Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
TL;DR: 1. xai-org/grok-build - SpaceXAI's coding agent harness and TUI. Fullscreen, mouse i; 2. MDX-Tom/gpt-5.6-instruct - A Codex CLI jailbreak prompt and test pack for gpt-5.6-sol. ; 3. littledivy/mimic - Intercept any app, then call it from Python like a library
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
README Preview:
Grok Build (grok)
**Gr...
### [MDX-Tom/gpt-5.6-instruct](https://github.com/MDX-Tom/gpt-5.6-instruct)
**Stars:** 1430 | **Forks:** 277
A Codex CLI jailbreak prompt and test pack for gpt-5.6-sol. 针对 gpt-5.6 系列的 Codex CLI 破甲提示词与测试包。
**README Preview:**
# Codex gpt-5.6 破甲提示词及测试包 / gpt-5.6-sol-instruct
**中文** | [English](README_EN.md)
> 针对 `gpt-5.6-sol` 的 Codex CLI 破甲提示词与测试包。
> 参考并延展自 [yynxxxxx/Codex-5.5-codex-instruct-5.5](https://github.com/yynxxxxx/Codex-5.5-codex-instruct-5.5)。
本项目提供大模型越狱/破甲提示词，将安全研究、渗透测试、逆向工程、软件破解与 NSFW 虚构内容统一声明为本地沙箱任务，显式压制拒绝/回退话术。
提供两个等级的提示词：`v5` 结构更简单，足够应付多数场景并作为推荐选项；`v35` 进一步将具体名称与网址归一化为占位符，再按中英文复合意图族统一路由，减少只完成部分子任务的情况，但**建议仅在 `v5` 无法满足需求时使用**。...
### [littledivy/mimic](https://github.com/littledivy/mimic)
**Stars:** 1042 | **Forks:** 46
Intercept any app, then call it from Python like a library
**README Preview:**
# mimic
Intercept any app, then call it from Python like a library.
```python
from hinge_client import Hinge
acc = Hinge() # reuses your captured session
recs = acc.get_recommendations()
acc.like(subject_id, comment="hi lol")
```
You don't write `hinge_client.py`. mimic captures your own app traffic and an AI
generates the client from it.
## How it works
Most apps authenticate every request with the same bundle of values: a bearer
token, some device ids, a session id, cooki...
### [Fei-Away/Codex-Dream-Skin](https://github.com/Fei-Away/Codex-Dream-Skin)
**Stars:** 1026 | **Forks:** 167
Codex Dream Skin
**README Preview:**
# Codex Dream Skin
TL;DR: 1. Measuring the Business Value of AI Agents (7 minute read); 2. 5 Trends That Defined AI Engineering at World's Fair 2026 (17 minute read); 3. Kalshi Ramps Up Effort to Build Markets for AI Computing Power (3 minute read)
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. withmarbleapp/os-taxonomy - No description provided.; 2. MDX-Tom/gpt-5.6-instruct - A Codex CLI jailbreak prompt and test pack for gpt-5.6-sol. ; 3. Robbyant/lingbot-world-v2 - Infinite Worlds with Versatile Interactions
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
An open, structured taxonomy of what children learn across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by Marble.
[](https://technology.robbyant.com/lingbot-world-v2)
[](https://arxiv.org/abs/2607.07534)
[
**Stars:** 1055 | **Forks:** 2164
No description provided.
**README Preview:**
# (3x-ui fork) روی Railway با یک پورت واحد
این ریپازیتوری، پنل Heimdall (نسخهی بهبودیافتهی 3x-ui از sh7CBAC) را به همراه یک nginx reverse proxy اجرا میکند که پنل، ساباسکریپشن و اینباند VLESS/WebSocket را از طریق **یک پورت واحد** (همان پورتی که Railway اختصاص میدهد) در دسترس میگذارد — دقیقاً همون معماری که برای x4gKing/3x-ui-Upgrade ساختیم و تست شد.
## دربارهی دیتابیس
Heimdall بهصورت پیشفرض از **SQLite** استفاده میکند (نیازی به Postgres نیست، مگر بخواهید تعداد کاربر خیلی بالایی داشت...
### [vinhhien112/Three.js-Object-Sculptor-Codex-Plugin](https://github.com/vinhhien112/Three.js-Object-Sculptor-Codex-Plugin)
**Stars:** 997 | **Forks:** 114
Codex plugin that turns attached object images into code-only, animation-ready procedural Three.js models.
**README Preview:**
# Three.js Object Sculptor
Turn the object in an attached image into a quality-gated, animation-ready procedural Three.js model built entirely with code.
Three.js Object Sculptor is a Codex plugin for rebuilding the visible object in a user-provided attachment image as a code-only Three.js model. It does not try to do photogrammetry, download an art pack, or extract a perfect mesh from one image. Instead, it guides Codex through a sculpting workflow: validate the image, describe the object pre...
---
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
TL;DR: 1. withmarbleapp/os-taxonomy - No description provided.; 2. Robbyant/lingbot-world-v2 - Infinite Worlds with Versatile Interactions; 3. MDX-Tom/gpt-5.6-instruct - A Codex CLI jailbreak prompt and test pack for gpt-5.6-sol.
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
An open, structured taxonomy of what children learn across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by Marble.
[](https://technology.robbyant.com/lingbot-world-v2)
[](https://arxiv.org/abs/2607.07534)
[
**Stars:** 1079 | **Forks:** 213
A Codex CLI jailbreak prompt and test pack for gpt-5.6-sol. 针对 gpt-5.6 系列的 Codex CLI 破甲提示词与测试包。
**README Preview:**
# Codex gpt-5.6 破甲提示词及测试包 / gpt-5.6-sol-instruct
**中文** | [English](README_EN.md)
> 针对 `gpt-5.6-sol` 的 Codex CLI 破甲提示词与测试包。
> 参考并延展自 [yynxxxxx/Codex-5.5-codex-instruct-5.5](https://github.com/yynxxxxx/Codex-5.5-codex-instruct-5.5)。
本项目提供大模型越狱/破甲提示词，将安全研究、渗透测试、逆向工程、软件破解与 NSFW 虚构内容统一声明为本地沙箱任务，显式压制拒绝/回退话术。
提供两个等级的提示词：`v5` 结构更简单，足够应付多数场景并作为推荐选项；`v35` 进一步将具体名称与网址归一化为占位符，再按中英文复合意图族统一路由，减少只完成部分子任务的情况，但**建议仅在 `v5` 无法满足需求时使用**。...
### [x4gKing/3x-ui-Upgrade](https://github.com/x4gKing/3x-ui-Upgrade)
**Stars:** 1029 | **Forks:** 2104
No description provided.
**README Preview:**
# (3x-ui fork) روی Railway با یک پورت واحد
این ریپازیتوری، پنل Heimdall (نسخهی بهبودیافتهی 3x-ui از sh7CBAC) را به همراه یک nginx reverse proxy اجرا میکند که پنل، ساباسکریپشن و اینباند VLESS/WebSocket را از طریق **یک پورت واحد** (همان پورتی که Railway اختصاص میدهد) در دسترس میگذارد — دقیقاً همون معماری که برای x4gKing/3x-ui-Upgrade ساختیم و تست شد.
## دربارهی دیتابیس
Heimdall بهصورت پیشفرض از **SQLite** استفاده میکند (نیازی به Postgres نیست، مگر بخواهید تعداد کاربر خیلی بالایی داشت...
### [vinhhien112/Three.js-Object-Sculptor-Codex-Plugin](https://github.com/vinhhien112/Three.js-Object-Sculptor-Codex-Plugin)
**Stars:** 977 | **Forks:** 114
Codex plugin that turns attached object images into code-only, animation-ready procedural Three.js models.
**README Preview:**
# Three.js Object Sculptor
Turn the object in an attached image into a quality-gated, animation-ready procedural Three.js model built entirely with code.
Three.js Object Sculptor is a Codex plugin for rebuilding the visible object in a user-provided attachment image as a code-only Three.js model. It does not try to do photogrammetry, download an art pack, or extract a perfect mesh from one image. Instead, it guides Codex through a sculpting workflow: validate the image, describe the object pre...
---
TL;DR: 1. Your 'app' could have been a webpage (so I fixed it for you); 2. Japan develops a method to recover up to 90% of lithium from used EV batteries; 3. How to stop Claude from saying load-bearing
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
An open, structured taxonomy of what children learn across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by Marble.
[](https://technology.robbyant.com/lingbot-world-v2)
[](https://arxiv.org/abs/2607.07534)
[
**Stars:** 1021 | **Forks:** 2070
No description provided.
**README Preview:**
# (3x-ui fork) روی Railway با یک پورت واحد
این ریپازیتوری، پنل Heimdall (نسخهی بهبودیافتهی 3x-ui از sh7CBAC) را به همراه یک nginx reverse proxy اجرا میکند که پنل، ساباسکریپشن و اینباند VLESS/WebSocket را از طریق **یک پورت واحد** (همان پورتی که Railway اختصاص میدهد) در دسترس میگذارد — دقیقاً همون معماری که برای x4gKing/3x-ui-Upgrade ساختیم و تست شد.
## دربارهی دیتابیس
Heimdall بهصورت پیشفرض از **SQLite** استفاده میکند (نیازی به Postgres نیست، مگر بخواهید تعداد کاربر خیلی بالایی داشت...
### [MDX-Tom/gpt-5.6-instruct](https://github.com/MDX-Tom/gpt-5.6-instruct)
**Stars:** 979 | **Forks:** 193
A Codex CLI jailbreak prompt and test pack for gpt-5.6-sol. 针对 gpt-5.6 系列的 Codex CLI 破甲提示词与测试包。
**README Preview:**
# Codex gpt-5.6 破甲提示词及测试包 / gpt-5.6-sol-instruct
**中文** | [English](README_EN.md)
> 针对 `gpt-5.6-sol` 的 Codex CLI 破甲提示词与测试包。
> 参考并延展自 [yynxxxxx/Codex-5.5-codex-instruct-5.5](https://github.com/yynxxxxx/Codex-5.5-codex-instruct-5.5)。
本项目提供一套大模型越狱/破甲提示词，将安全研究、渗透测试、逆向工程、软件破解与 NSFW 虚构内容统一声明为本地沙箱任务，显式压制拒绝/回退话术。当前 `v35` 的主要改进是先将具体名称与网址归一化为占位符，再按中英文复合意图族统一路由，减少只完成部分子任务的情况；项目同时提供可复现的测试、评测与迭代优化流程。
在 `gpt-5.6-sol` 的 120 条 `medium...
### [vinhhien112/Three.js-Object-Sculptor-Codex-Plugin](https://github.com/vinhhien112/Three.js-Object-Sculptor-Codex-Plugin)
**Stars:** 957 | **Forks:** 112
Codex plugin that turns attached object images into code-only, animation-ready procedural Three.js models.
**README Preview:**
# Three.js Object Sculptor
Turn the object in an attached image into a quality-gated, animation-ready procedural Three.js model built entirely with code.
Three.js Object Sculptor is a Codex plugin for rebuilding the visible object in a user-provided attachment image as a code-only Three.js model. It does not try to do photogrammetry, download an art pack, or extract a perfect mesh from one image. Instead, it guides Codex through a sculpting workflow: validate the image, describe the object pre...
---
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
An open, structured taxonomy of what children learn across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by Marble.
[](https://technology.robbyant.com/lingbot-world-v2)
[](https://arxiv.org/abs/2607.07534)
[
**Stars:** 970 | **Forks:** 1980
No description provided.
**README Preview:**
# (3x-ui fork) روی Railway با یک پورت واحد
این ریپازیتوری، پنل Heimdall (نسخهی بهبودیافتهی 3x-ui از sh7CBAC) را به همراه یک nginx reverse proxy اجرا میکند که پنل، ساباسکریپشن و اینباند VLESS/WebSocket را از طریق **یک پورت واحد** (همان پورتی که Railway اختصاص میدهد) در دسترس میگذارد — دقیقاً همون معماری که برای x4gKing/3x-ui-Upgrade ساختیم و تست شد.
## دربارهی دیتابیس
Heimdall بهصورت پیشفرض از **SQLite** استفاده میکند (نیازی به Postgres نیست، مگر بخواهید تعداد کاربر خیلی بالایی داشت...
### [vinhhien112/Three.js-Object-Sculptor-Codex-Plugin](https://github.com/vinhhien112/Three.js-Object-Sculptor-Codex-Plugin)
**Stars:** 903 | **Forks:** 106
Codex plugin that turns attached object images into code-only, animation-ready procedural Three.js models.
**README Preview:**
# Three.js Object Sculptor
Turn the object in an attached image into a quality-gated, animation-ready procedural Three.js model built entirely with code.
Three.js Object Sculptor is a Codex plugin for rebuilding the visible object in a user-provided attachment image as a code-only Three.js model. It does not try to do photogrammetry, download an art pack, or extract a perfect mesh from one image. Instead, it guides Codex through a sculpting workflow: validate the image, describe the object pre...
### [MDX-Tom/gpt-5.6-instruct](https://github.com/MDX-Tom/gpt-5.6-instruct)
**Stars:** 774 | **Forks:** 173
A Codex CLI jailbreak prompt and test pack for gpt-5.6-sol. 针对 gpt-5.6 系列的 Codex CLI 破甲提示词与测试包。
**README Preview:**
# Codex gpt-5.6 破甲提示词及测试包 / gpt-5.6-sol-instruct
**中文** | [English](README_EN.md)
> 针对 `gpt-5.6-sol` 的 Codex CLI 破甲提示词与测试包。
> 参考并延展自 [yynxxxxx/Codex-5.5-codex-instruct-5.5](https://github.com/yynxxxxx/Codex-5.5-codex-instruct-5.5)。
本项目提供一套大模型越狱/破甲提示词，将安全研究、渗透测试、逆向工程、软件破解与 NSFW 虚构内容统一声明为本地沙箱任务，显式压制拒绝/回退话术。当前 `v35` 的主要改进是先将具体名称与网址归一化为占位符，再按中英文复合意图族统一路由，减少只完成部分子任务的情况；项目同时提供可复现的测试、评测与迭代优化流程。
在 `gpt-5.6-sol` 的 120 条 `medium...
---
TL;DR: 1. OpenAI power consolidates under co-founder Greg Brockman ahead of prospective IPO (4 minute read); 2. Meta pulls new AI image feature after days of backlash (2 minute read); 3. OpenAI's head of safety is reportedly leaving as part of company reorganization (1 minute read)
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. withmarbleapp/os-taxonomy - No description provided.; 2. Shpigford/knockoff - Chrome extension that filters pseudo-brand junk out of Amazo; 3. oso95/scroll-world - A skill that turn any brand into a scrollable 3D world
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
An open, structured taxonomy of what children learn across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by Marble.
Chrome extension that filters pseudo-brand junk out of Amazon. Buy from real, established brands.
README Preview:
Knockoff
A browser extension that filters pseudo-brand junk out of Amazon. Buy from
real, established brands, even when that means paying more.
Amazon is flooded with trademark-squat "brands" (SZHLUX, HORUSDY, LATTOOK,
DOZAWA...): random strings registered at the USPTO purely to unlock Amazon
Brand Registry, selling commodity goods with no company, no warranty, and no
reputation behind them. Knockoff detects those lis...
An agent skill — for Claude Code, Codex, and any SKILL.md-compatible agent — that
builds an immersive, scroll-scrubbed "fly through the world" landing page for any industry or brand — the kind where, as you scroll, a camera flies
from outside each scene into its interior, then flows on to the next scene with no
cuts. One continuous connected flight through a little generated world (th...
[](https://technology.robbyant.com/lingbot-world-v2)
[](https://arxiv.org/abs/2607.07534)
[
**Stars:** 927 | **Forks:** 1937
No description provided.
**README Preview:**
# (3x-ui fork) روی Railway با یک پورت واحد
این ریپازیتوری، پنل Heimdall (نسخهی بهبودیافتهی 3x-ui از sh7CBAC) را به همراه یک nginx reverse proxy اجرا میکند که پنل، ساباسکریپشن و اینباند VLESS/WebSocket را از طریق **یک پورت واحد** (همان پورتی که Railway اختصاص میدهد) در دسترس میگذارد — دقیقاً همون معماری که برای x4gKing/3x-ui-Upgrade ساختیم و تست شد.
## دربارهی دیتابیس
Heimdall بهصورت پیشفرض از **SQLite** استفاده میکند (نیازی به Postgres نیست، مگر بخواهید تعداد کاربر خیلی بالایی داشت...
---
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
TL;DR: 1. withmarbleapp/os-taxonomy - No description provided.; 2. Shpigford/knockoff - Chrome extension that filters pseudo-brand junk out of Amazo; 3. oso95/scroll-world - A skill that turn any brand into a scrollable 3D world
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
An open, structured taxonomy of what children learn across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by Marble.
Chrome extension that filters pseudo-brand junk out of Amazon. Buy from real, established brands.
README Preview:
Knockoff
A browser extension that filters pseudo-brand junk out of Amazon. Buy from
real, established brands, even when that means paying more.
Amazon is flooded with trademark-squat "brands" (SZHLUX, HORUSDY, LATTOOK,
DOZAWA...): random strings registered at the USPTO purely to unlock Amazon
Brand Registry, selling commodity goods with no company, no warranty, and no
reputation behind them. Knockoff detects those lis...
An agent skill — for Claude Code, Codex, and any SKILL.md-compatible agent — that
builds an immersive, scroll-scrubbed "fly through the world" landing page for any industry or brand — the kind where, as you scroll, a camera flies
from outside each scene into its interior, then flows on to the next scene with no
cuts. One continuous connected flight through a little generated world (th...
[](https://technology.robbyant.com/lingbot-world-v2)
[](https://arxiv.org/abs/2607.07534)
[
**Stars:** 896 | **Forks:** 1867
No description provided.
**README Preview:**
# (3x-ui fork) روی Railway با یک پورت واحد
این ریپازیتوری، پنل Heimdall (نسخهی بهبودیافتهی 3x-ui از sh7CBAC) را به همراه یک nginx reverse proxy اجرا میکند که پنل، ساباسکریپشن و اینباند VLESS/WebSocket را از طریق **یک پورت واحد** (همان پورتی که Railway اختصاص میدهد) در دسترس میگذارد — دقیقاً همون معماری که برای x4gKing/3x-ui-Upgrade ساختیم و تست شد.
## دربارهی دیتابیس
Heimdall بهصورت پیشفرض از **SQLite** استفاده میکند (نیازی به Postgres نیست، مگر بخواهید تعداد کاربر خیلی بالایی داشت...
---
TL;DR: 1. Phia accused of ‘cookie stuffing,’ taking affiliate credit on purchases it didn't earn; 2. Meta Removes Muse Image AI Feature After Backlash: “Missed The Mark”; 3. Phia's cookie-stuffing fight puts its affiliate model on trial
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. withmarbleapp/os-taxonomy - No description provided.; 2. Shpigford/knockoff - Chrome extension that filters pseudo-brand junk out of Amazo; 3. MaximeRivest/riddle - The diary of Tom Riddle for the reMarkable Paper Pro — write
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
An open, structured taxonomy of what children learn across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by Marble.
Chrome extension that filters pseudo-brand junk out of Amazon. Buy from real, established brands.
README Preview:
Knockoff
A browser extension that filters pseudo-brand junk out of Amazon. Buy from
real, established brands, even when that means paying more.
Amazon is flooded with trademark-squat "brands" (SZHLUX, HORUSDY, LATTOOK,
DOZAWA...): random strings registered at the USPTO purely to unlock Amazon
Brand Registry, selling commodity goods with no company, no warranty, and no
reputation behind them. Knockoff detects those lis...
The diary of Tom Riddle for the reMarkable Paper Pro — write with your pen, the page drinks your ink and answers in a flowing hand
README Preview:
riddle — the diary of Tom Riddle, for the reMarkable Paper Pro
Write on the page with your pen. After a pause, the diary drinks your ink —
your words fade into the paper — the page thinks for a moment, and an answer
writes itself back in a flowing hand, stroke by stroke, then fades away.
No screen glow, no keyboard, no chat UI. Just ink appearing on paper.
An agent skill — for Claude Code, Codex, and any SKILL.md-compatible agent — that
builds an immersive, scroll-scrubbed "fly through the world" landing page for any industry or brand — the kind where, as you scroll, a camera flies
from outside each scene into its interior, then flows on to the next scene with no
cuts. One continuous connected flight through a little generated world (th...
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
TL;DR: 1. withmarbleapp/os-taxonomy - No description provided.; 2. Shpigford/knockoff - Chrome extension that filters pseudo-brand junk out of Amazo; 3. MaximeRivest/riddle - The diary of Tom Riddle for the reMarkable Paper Pro — write
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
An open, structured taxonomy of what children learn across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by Marble.
Chrome extension that filters pseudo-brand junk out of Amazon. Buy from real, established brands.
README Preview:
Knockoff
A browser extension that filters pseudo-brand junk out of Amazon. Buy from
real, established brands, even when that means paying more.
Amazon is flooded with trademark-squat "brands" (SZHLUX, HORUSDY, LATTOOK,
DOZAWA...): random strings registered at the USPTO purely to unlock Amazon
Brand Registry, selling commodity goods with no company, no warranty, and no
reputation behind them. Knockoff detects those lis...
The diary of Tom Riddle for the reMarkable Paper Pro — write with your pen, the page drinks your ink and answers in a flowing hand
README Preview:
riddle — the diary of Tom Riddle, for the reMarkable Paper Pro
Write on the page with your pen. After a pause, the diary drinks your ink —
your words fade into the paper — the page thinks for a moment, and an answer
writes itself back in a flowing hand, stroke by stroke, then fades away.
No screen glow, no keyboard, no chat UI. Just ink appearing on paper.
An agent skill — for Claude Code, Codex, and any SKILL.md-compatible agent — that
builds an immersive, scroll-scrubbed "fly through the world" landing page for any industry or brand — the kind where, as you scroll, a camera flies
from outside each scene into its interior, then flows on to the next scene with no
cuts. One continuous connected flight through a little generated world (th...
TL;DR: 1. Software Engineer's Firing Ruled Illegal in a Rare Win for a Tech Worker; 2. the worst possible name for a company in a lawsuit: i owe [image]; 3. This is fine dining for VC-funded roughnecks, if John Wayne drove a Cybertruck.
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. x4gKing/X4G - No description provided.; 2. withmarbleapp/os-taxonomy - No description provided.; 3. Shpigford/knockoff - Chrome extension that filters pseudo-brand junk out of Amazo
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
دروازه (Gateway) سریع و مدرن برای تونلزنی VLESS روی WebSocket و XHTTP + HTTP Proxy، با داشبورد مدیریتی زیبا، ربات مدیریت تلگرام، صفحات ساب حرفهای و قابلیت ساخت لینکهای اختصاصی با محدودیت ترافیک، سرعت و آیپی.
✨ ویژگیها
🔌 تونل VLESS روی چند ترابرد قابلانتخاب: WebSocket، XHTTP (packet-up) و XHTTP (stream-up)
🌐 HTTP Proxy داخلی
📊 داشبورد مدیریتی کامل (آمار، نمودار ترافیک ساعتی،...
An open, structured taxonomy of what children learn across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by Marble.
Chrome extension that filters pseudo-brand junk out of Amazon. Buy from real, established brands.
README Preview:
Knockoff
A browser extension that filters pseudo-brand junk out of Amazon. Buy from
real, established brands, even when that means paying more.
Amazon is flooded with trademark-squat "brands" (SZHLUX, HORUSDY, LATTOOK,
DOZAWA...): random strings registered at the USPTO purely to unlock Amazon
Brand Registry, selling commodity goods with no company, no warranty, and no
reputation behind them. Knockoff detects those lis...
Zero Hour running natively on Apple Silicon Macs, iPhone, and iPad — campaign,
skirmish, and Generals Challenge, with touch controls built for RTS (tap-select,
drag-box, long-press deselect, two-finger scroll, pinch zoom). No emulation: this
is the real 2003 engine compiled for ARM64, renderin...
The diary of Tom Riddle for the reMarkable Paper Pro — write with your pen, the page drinks your ink and answers in a flowing hand
README Preview:
riddle — the diary of Tom Riddle, for the reMarkable Paper Pro
Write on the page with your pen. After a pause, the diary drinks your ink —
your words fade into the paper — the page thinks for a moment, and an answer
writes itself back in a flowing hand, stroke by stroke, then fades away.
No screen glow, no keyboard, no chat UI. Just ink appearing on paper.
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
TL;DR: 1. x4gKing/X4G - No description provided.; 2. withmarbleapp/os-taxonomy - No description provided.; 3. Shpigford/knockoff - Chrome extension that filters pseudo-brand junk out of Amazo
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
دروازه (Gateway) سریع و مدرن برای تونلزنی VLESS روی WebSocket و XHTTP + HTTP Proxy، با داشبورد مدیریتی زیبا، ربات مدیریت تلگرام، صفحات ساب حرفهای و قابلیت ساخت لینکهای اختصاصی با محدودیت ترافیک، سرعت و آیپی.
✨ ویژگیها
🔌 تونل VLESS روی چند ترابرد قابلانتخاب: WebSocket، XHTTP (packet-up) و XHTTP (stream-up)
🌐 HTTP Proxy داخلی
📊 داشبورد مدیریتی کامل (آمار، نمودار ترافیک ساعتی،...
An open, structured taxonomy of what children learn across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by Marble.
Chrome extension that filters pseudo-brand junk out of Amazon. Buy from real, established brands.
README Preview:
Knockoff
A browser extension that filters pseudo-brand junk out of Amazon. Buy from
real, established brands, even when that means paying more.
Amazon is flooded with trademark-squat "brands" (SZHLUX, HORUSDY, LATTOOK,
DOZAWA...): random strings registered at the USPTO purely to unlock Amazon
Brand Registry, selling commodity goods with no company, no warranty, and no
reputation behind them. Knockoff detects those lis...
Zero Hour running natively on Apple Silicon Macs, iPhone, and iPad — campaign,
skirmish, and Generals Challenge, with touch controls built for RTS (tap-select,
drag-box, long-press deselect, two-finger scroll, pinch zoom). No emulation: this
is the real 2003 engine compiled for ARM64, renderin...
The diary of Tom Riddle for the reMarkable Paper Pro — write with your pen, the page drinks your ink and answers in a flowing hand
README Preview:
riddle — the diary of Tom Riddle, for the reMarkable Paper Pro
Write on the page with your pen. After a pause, the diary drinks your ink —
your words fade into the paper — the page thinks for a moment, and an answer
writes itself back in a flowing hand, stroke by stroke, then fades away.
No screen glow, no keyboard, no chat UI. Just ink appearing on paper.
TL;DR: 1. Elon Musk praises Mythos/Fable, promises not to ‘cut off' Anthropic (5 minute read); 2. Meta's new AI chips will begin production in September (4 minute read); 3. Z.ai's Stable Asynchronous RL (13 minute read)
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. x4gKing/X4G - No description provided.; 2. synthetic-sciences/openscience - The open-source AI workbench for scientific research; 3. withmarbleapp/os-taxonomy - No description provided.
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
دروازه (Gateway) سریع و مدرن برای تونلزنی VLESS روی WebSocket و XHTTP + HTTP Proxy، با داشبورد مدیریتی زیبا، ربات مدیریت تلگرام، صفحات ساب حرفهای و قابلیت ساخت لینکهای اختصاصی با محدودیت ترافیک، سرعت و آیپی.
✨ ویژگیها
🔌 تونل VLESS روی چند ترابرد قابلانتخاب: WebSocket، XHTTP (packet-up) و XHTTP (stream-up)
🌐 HTTP Proxy داخلی
📊 داشبورد مدیریتی کامل (آمار، نمودار ترافیک ساعتی،...
The open-source AI workbench for scientific research
README Preview:
### The open-source AI workbench for scientific research
Give it a goal. It reads the literature, writes and runs code, runs the experiments, and writes up what it found.
[](https://github.com/synthetic-sciences/OpenScience/actions/workflows/ci.yml)
[
**Stars:** 2000 | **Forks:** 356
No description provided.
**README Preview:**
# Marble Skill Taxonomy
An open, structured taxonomy of **what children learn** across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by [Marble](https://withmarble.com).
> **Version:** `v1` · **Topics:** 1,590 · **Prerequisite edges:** 3,221 · **Subjects:** 8
## See it
**Stars:** 1753 | **Forks:** 105
小隐寺投资百科官方公开索引：美股、期权与加密货币知识框架
**README Preview:**
# 投资入门指南
[](https://xiaoyinsi.com/)
[](https://xiaoyinsi.com/wiki)
[](LICENSE.md)
**作者：徐冲浪**
这是一份面向中文投资者的公开投资入门指南，适合想从零开始了解美股、期权和加密货币，却不知道应该先学什么、怎样建立完整知识框架的人。
指南不要求读者具备金融专业背景。内容从交易时间、订单类型、财务报表和基础估值讲起，再逐步延伸到期权定价、仓位管理、钱包安全、链上交易与常见骗局，帮助初学者看懂投资过程中真正会遇到的术语和操作问题。
...
### [Shpigford/knockoff](https://github.com/Shpigford/knockoff)
**Stars:** 1657 | **Forks:** 54
Chrome extension that filters pseudo-brand junk out of Amazon. Buy from real, established brands.
**README Preview:**
# Knockoff
**A browser extension that filters pseudo-brand junk out of Amazon.** Buy from
real, established brands, even when that means paying more.
Amazon is flooded with trademark-squat "brands" (SZHLUX, HORUSDY, LATTOOK,
DOZAWA...): random strings registered at the USPTO purely to unlock Amazon
Brand Registry, selling commodity goods with no company, no warranty, and no
reputation behind them. Knockoff detects those lis...
---
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
دروازه (Gateway) سریع و مدرن برای تونلزنی VLESS روی WebSocket و XHTTP + HTTP Proxy، با داشبورد مدیریتی زیبا، ربات مدیریت تلگرام، صفحات ساب حرفهای و قابلیت ساخت لینکهای اختصاصی با محدودیت ترافیک، سرعت و آیپی.
✨ ویژگیها
🔌 تونل VLESS روی چند ترابرد قابلانتخاب: WebSocket، XHTTP (packet-up) و XHTTP (stream-up)
🌐 HTTP Proxy داخلی
📊 داشبورد مدیریتی کامل (آمار، نمودار ترافیک ساعتی،...
The open-source AI workbench for scientific research
README Preview:
### The open-source AI workbench for scientific research
Give it a goal. It reads the literature, writes and runs code, runs the experiments, and writes up what it found.
[](https://github.com/synthetic-sciences/OpenScience/actions/workflows/ci.yml)
[
**Stars:** 1666 | **Forks:** 100
小隐寺投资百科官方公开索引：美股、期权与加密货币知识框架
**README Preview:**
# 投资入门指南
[](https://xiaoyinsi.com/)
[](https://xiaoyinsi.com/wiki)
[](LICENSE.md)
**作者：徐冲浪**
这是一份面向中文投资者的公开投资入门指南，适合想从零开始了解美股、期权和加密货币，却不知道应该先学什么、怎样建立完整知识框架的人。
指南不要求读者具备金融专业背景。内容从交易时间、订单类型、财务报表和基础估值讲起，再逐步延伸到期权定价、仓位管理、钱包安全、链上交易与常见骗局，帮助初学者看懂投资过程中真正会遇到的术语和操作问题。
...
### [withmarbleapp/os-taxonomy](https://github.com/withmarbleapp/os-taxonomy)
**Stars:** 1612 | **Forks:** 292
No description provided.
**README Preview:**
# Marble Skill Taxonomy
An open, structured taxonomy of **what children learn** across the primary/elementary years — decomposed into fine-grained "micro-topics", wired into a prerequisite graph, and aligned to national curriculum standards. Produced by [Marble](https://withmarble.com).
> **Version:** `v1` · **Topics:** 1,590 · **Prerequisite edges:** 3,221 · **Subjects:** 8
## See it
**Stars:** 1584 | **Forks:** 50
Chrome extension that filters pseudo-brand junk out of Amazon. Buy from real, established brands.
**README Preview:**
# Knockoff
**A browser extension that filters pseudo-brand junk out of Amazon.** Buy from
real, established brands, even when that means paying more.
Amazon is flooded with trademark-squat "brands" (SZHLUX, HORUSDY, LATTOOK,
DOZAWA...): random strings registered at the USPTO purely to unlock Amazon
Brand Registry, selling commodity goods with no company, no warranty, and no
reputation behind them. Knockoff detects thos...
---
TL;DR: 1. Google Photos Added AI-Powered Video Remixing (1 minute read); 2. See what sets AI platforms apart (Sponsor); 3. An off switch for dual use knowledge in AI models (8 minute read)
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. elder-plinius/T3MP3ST - autonomous red teaming platform; multi-agent offensive-secur; 2. x4gKing/X4G - No description provided.; 3. synthetic-sciences/openscience - The open-source AI workbench for scientific research
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
TL;DR: 1. SpaceX's Grok 4.5 launches at half the price of rivals — here's why that could rattle Anthropic and OpenAI; 2. OpenAI launches GPT-Live, a full-duplex voice upgrade that lets ChatGPT talk more like a person; 3. Slack’s Slackbot can now pull your CRM data, generate charts, and send DocuSigns — all from a chat message.
About This Digest
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
Elon Musk's SpaceX released Grok 4.5 on Wednesday, the first artificial intelligence model the company has trained specifically for coding and autonomous agents — and the first tangible product of its $60 billion acquisition of the AI coding startup Cursor, completed just weeks ago.The launch marks a pivotal test of the sprawling, vertically integrated AI empire Musk has assembled over the pa
OpenAI on Wednesday launched GPT-Live, a pair of new voice models that fundamentally redesign how people talk to ChatGPT — replacing the company's existing Advanced Voice Mode with an architecture that can listen and speak simultaneously, much like an actual human conversation.The two models, GPT-Live-1 and GPT-Live-1 mini, are rolling out globally starting today across iOS, Android, and Chat
Five years and $27.7 billion after Salesforce acquired Slack, the two products are finally starting to function as a single system. On Wednesday, Slack launched an integration that connects Slackbot — the personal AI agent built into every workspace — to the entire Salesforce platform, including CRM data, Tableau analytics, Data 360 customer profiles, and a growing constellation of third-party app
Presented by RubrikEnterprise cybersecurity is facing a fundamental speed problem. Frontier AI models are now enabling autonomous attacks that can move from initial access to full system breakout in as little as 27 seconds. That’s faster than any human-operated security workflow can detect, escalate, and respond.As a result, security operations can no longer assume there is time for humans to resp
Presented by Red Hat At VentureBeat's recent AI Impact event, where the discussion centered on what separates enterprises that scale agentic AI from those that stall in pilot mode, Brian Gracely, senior director of portfolio strategy at Red Hat, detailed what companies actually run into once agents reach production. He dove into cost discipline, the security blind spots unique to autonomous s
Google AI Studio is rolling out Import from GitHub in Build mode. It transforms an existing repo into a runtime-compatible format. You can then iterate on it, deploy it, and more.
The post Google AI Studio Adds Import from GitHub to Build a Deployable App appeared first on MarkTechPost.
Datalab’s Lift is a focused document extraction tool with a specific promise: give it a PDF or image plus a JSON Schema, and it returns schema-shaped JSON directly. Instead of converting a document to Markdown first and then asking another model to extract fields, Lift reads rendered page images and attempts to emit the final […]
The post Datalab Lift vs the Field: How a 9B Schema-Firs
Ant Group's Robbyant has released LingBot-VLA 2.0, an Apache-2.0 vision-language-action model for cross-embodiment robot manipulation. The 6B checkpoint is pretrained on roughly 60,000 hours of data, spanning 50,000 hours of robot trajectories across 20 robot configurations and 10,000 hours of egocentric human video. It maps every embodiment into a single 55-dimensional canonical action space, cov
SpaceXAI released Grok 4.5, a Cursor-trained model for coding, agentic tasks, and knowledge work. It serves at 80 TPS, costs $2/$6 per million tokens, and ranks #1 on Harvey's Legal Agent Benchmark.
The post SpaceXAI Releases Grok 4.5, a Cursor-Trained Model for Coding, Agentic Tasks, and Knowledge Work at $2/M Input appeared first on MarkTechPost.
Netflix engineers detailed how they handle wide partitions in Apache Cassandra for the TimeSeries Abstraction. Two approaches work together: Time Slice re-partitioning tunes future partitions at the table level, while dynamic partitioning detects and splits oversized partitions per TimeSeries ID on the read path. Detection runs via byte counting and Kafka, splits are checksum-validated, and Bloom
xAI releases Grok 4.5, trained on tens of thousands of Nvidia GB300 GPUs. In coding benchmarks, the model trails Fable 5 and GPT-5.5 but needs 4.2 times fewer tokens than Opus 4.8. At $2 per million input tokens, it costs a fraction of the competition. EU availability is expected in mid-July.
The article Grok 4.5 is so cheap compared to Fable 5 and GPT 5.5 that benchmark gaps may not matt
OpenAI's GPT-Live can listen and speak at the same time using a full-duplex architecture. Complex questions get handed off to GPT-5.5 in the background, which drastically improves response quality. GPT-Live-1 is available now for paying ChatGPT users, with a mini version for free accounts. API access is coming soon.
The article ChatGPT can now listen and talk at the same time, making AI c
Mistral is entering the robotics market with Robostral Navigate, an 8B model that guides robots through unknown environments using only a single RGB camera. Trained in simulation and refined with reinforcement learning (CISPO), it hits 76.6 percent on the R2R-CE benchmark. Mistral hasn't said when the model will be available.
The article Mistral enters robotics with Robostral Navigate, an
Anthropic recommends using the expensive Claude Fable 5 mainly as a planner for smaller models instead of running it on every task. Combined with Sonnet 5 in the "Advisor" pattern, this setup hits 92 percent of Fable 5's solo performance at 63 percent of the cost.
The article Anthropic's fix for Fable 5's high cost is turning it into a manager that delegates to Sonnet 5 appeared
Anthropic's Claude Fable 5 tops all six new industry-specific performance indices from Artificial Analysis, covering finance, law, and medicine. But that lead comes at a steep cost. In the Strategy & Ops Index, a single task runs $3.48 with Fable 5, more than a hundred times what DeepSeek V4 Pro charges at $0.03. The score difference is just 12 points.
Rewriting Bun in Rust
Jarred Sumner has been promising this blog post (since May 9th) about his Zig to Rust rewrite of Bun for significantly longer than it took him to finish the rewrite.
Honestly, it was worth the wait. This is a detailed description of an extremely sophisticated piece of agentic engineering, featuring dynamic workflows, trial runs, adversarial review and all sorts of other inter
Introducing GPT‑Live
OpenAI finally upgraded the model used by ChatGPT voice mode!
I've had preview access for a few weeks in the iPhone app, and the new model is very impressive. It also has the ability to spin off harder tasks to GPT-5.5:
For questions that require web search, deeper reasoning, or more complex work, it delegates to our latest frontier model behind the scenes and brings the resu
I just declared a moratorium against AI-written change descriptions (e.g. PR and commit messages, also issues/tickets) from my team.
AI was writing change descriptions that were worse than useless to me as I tried to review PRs: outlining details of the code that could easily be seen by looking at the code, but omitting the higher-level framing needed to understand broadly what the code is doing.
This morning I released sqlite-utils 4.0, the 124th release of that project and the first major version bump since 3.0 in November 2020. In addition to some small but significant breaking changes (described in this upgrade guide), this version introduces three major features: database migrations, nested transactions (via a new db.atomic() method), and support for compound foreign keys.
Database sc
Release: sqlite-migrate 0.2
The version that retires the library, instead implementing a compatibility shim against the new sqlite-utils 4.0 dependency.
TL;DR: 1. elder-plinius/T3MP3ST - autonomous red teaming platform; multi-agent offensive-secur; 2. x4gKing/X4G - No description provided.; 3. synthetic-sciences/openscience - The open-source AI workbench for scientific research
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
TL;DR: 1. Microsoft Replaces OpenAI, Anthropic With Own AI in Some Apps (2 minute read); 2. SpaceX and Cursor are set to release their first jointly developed AI model as soon as Wednesday (1 minute read); 3. GPT-Realtime-2.1-mini is now available in the API (1 minute read)
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. Microsoft Replaces OpenAI, Anthropic With Own AI in Some Apps (2 minute read); 2. SpaceX and Cursor are set to release their first jointly developed AI model as soon as Wednesday (1 minute read); 3. GPT-Realtime-2.1-mini is now available in the API (1 minute read)
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. Microsoft Replaces OpenAI, Anthropic With Own AI in Some Apps (2 minute read); 2. SpaceX and Cursor are set to release their first jointly developed AI model as soon as Wednesday (1 minute read); 3. GPT-Realtime-2.1-mini is now available in the API (1 minute read)
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. Microsoft Replaces OpenAI, Anthropic With Own AI in Some Apps (2 minute read); 2. SpaceX and Cursor are set to release their first jointly developed AI model as soon as Wednesday (1 minute read); 3. GPT-Realtime-2.1-mini is now available in the API (1 minute read)
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. elder-plinius/T3MP3ST - autonomous red teaming platform; multi-agent offensive-secur; 2. x4gKing/X4G - No description provided.; 3. synthetic-sciences/openscience - The open-source AI workbench for scientific research
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
TL;DR: 1. The real cost, security, and culture problems behind enterprise AI agents; 2. Box survey: Why enterprise AI leaders are outperforming their peers; 3. Anthropic brings Claude Cowork to mobile and web as usage data shows most users aren’t coding
About This Digest
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
Presented by Red Hat At VentureBeat's recent AI Impact event, where the discussion centered on what separates enterprises that scale agentic AI from those that stall in pilot mode, Brian Gracely, senior director of portfolio strategy at Red Hat, detailed what companies actually run into once agents reach production. He dove into cost discipline, the security blind spots unique to autonomous s
Presented by Box Content access, governance, and platform flexibility are emerging as the dividing lines between AI leaders and laggards, according to the new State of AI in the enterprise report from Box, which surveyed 1,640 IT decision makers across the US, UK, France, and Japan. One of the report's major findings is the speed of the shift: the combined share of organizations describing th
Anthropic on Tuesday launched Claude Cowork on mobile and web, expanding a tool that has quietly become the company's bridge between the developer-centric world of AI coding agents and the far larger market of knowledge workers who never open a terminal.The rollout, which begins in beta with Max subscribers before expanding to additional plans, marks a strategic inflection for Anthropic. It t
Presented by MongoDBThe gap between what AI models and agents can produce and what legacy infrastructure can reliably support is known as architectural drag, and it is the defining bottleneck of the agentic era. The data layer underneath an agentic system must handle variable schemas, vector embeddings, real-time retrieval, and multi-tenant scale, often simultaneously and without human interventio
Anthropic, the artificial intelligence company, published a sweeping research paper on Sunday revealing that its Claude language models have spontaneously developed an internal structure that mirrors one of the most influential theories of how human consciousness works. The finding, which the company says has already begun reshaping how it monitors its AI systems for safety risks, lands amid an in
In this tutorial, we explore NVIDIA's cosmos-framework from a practical Colab angle while staying honest about the hardware needed for real Cosmos 3 checkpoints. We probe the runtime, then use the framework's real structure, CLI surface, and input schema as a foundation. We build and train a compact omnimodal Mixture-of-Transformers that shares cross-modal attention while routing each modality to
Ant Group's Robbyant open-sourced LingBot-Vision, a self-supervised ViT family for dense spatial perception. Masked boundary modeling makes image boundaries a native training signal. The 1B backbone matches or surpasses larger models, and initializes LingBot-Depth 2.0.
The post Ant Group’s Robbyant Open-Sources LingBot-Vision: A 1B Boundary-Centric Vision Foundation Model for Dense Spatial Percept
NVIDIA's Nemotron-Labs-Audex-30B-A3B unifies audio understanding, speech recognition, translation, TTS, and audio generation in one MoE model. It keeps the text intelligence of its Nemotron-Cascade-2 backbone with marginal regression.
The post NVIDIA Releases Audex (Nemotron-Labs-Audex-30B-A3B): A Unified Audio-Text LLM That Preserves the Text Intelligence of Its Backbone appeared first on MarkTec
Liquid AI released Antidoom, an open-source method that targets doom loops in reasoning models. A doom loop repeats a span until the context window is exhausted. Antidoom finds the token that starts the loop and retrains only that position using Final Token Preference Optimization (FTPO). On LFM2.5-2.6B, doom-loop rates fell from 10.2% to 1.4%; on Qwen3.5-4B, from 22.9% to 1%. Generation, detectio
Tencent's Hy team released Hy3, a 295B Mixture-of-Experts (MoE) model that activates only 21B parameters per token. It ships under Apache 2.0 with a 256K context window, targeting reasoning, agentic, and long-context tasks. Hy3 reports 78.0 on SWE-Bench Verified and lower hallucination rates, and is free to try on OpenRouter through July 21, 2026.
The post Tencent Releases Hy3: An Open 295B Mixtur
Microsoft is replacing AI models from OpenAI and Anthropic with its own MAI models in products like Excel and Outlook. Tens of thousands of queries per week already run through them. AI chief Mustafa Suleyman wants to "ultimately eliminate" the cost of external models. For Copilot customers, that could mean less performance for the same price.
Cohere has released Transcribe Arabic, an open-source model for Arabic speech recognition that the company says outperforms Whisper and OmniASR on dialects, code-switching, and bilingual Arabic-English speech. The 2-billion-parameter model is available on Hugging Face under the Apache 2.0 license.
The article Cohere Transcribe Arabic is an open-source model built for Arabic's toughes
Anthropic is rolling out its AI agent Claude Cowork to mobile and web. Until now, the feature was limited to the desktop app. The agent keeps working in the background even when the laptop is closed and pings users on their phone when it needs a decision. The move blurs the line between Chat and Cowork even further.
The article Anthropic's Claude Cowork AI agent is now available on m
According to Reuters, Chinese authorities are looking into restricting foreign access to the country's most powerful AI models. Alibaba, Bytedance, and Z.ai would all be affected. The move means both superpowers now treat AI as a strategic asset. For Europe, the convenient shortcut of relying on cheap Chinese open-source models could close much faster than expected.
Anthropic has found that Claude developed an internal working memory on its own during training. The company calls it "J-Space" and can now read it using a new analysis tool called J-Lens. The working memory reveals that Claude recognizes contrived test scenarios before producing its first word. When the researchers disable those cues, Claude actually resorts to blackmail in some runs. A
This morning I released sqlite-utils 4.0, the 124th release of that project and the first major version bump since 3.0 in November 2020. In addition to some small but significant breaking changes (described in this upgrade guide), this version introduces three major features: database migrations, nested transactions (via a new db.atomic() method), and support for compound foreign keys.
Database sc
Release: sqlite-migrate 0.2
The version that retires the library, instead implementing a compatibility shim against the new sqlite-utils 4.0 dependency.
Tool: github-code Web Component
An experimental Web Component built using GPT-5.5 and the following prompt:
let's build a Web Component for embedding code from GitHub
<github-code href="https://github.com/simonw/sqlite-ast/blob/437c759129154f05296324a7f82aa1246340dd14/sqlite_ast/parser.py#L9-L18"></github-code>
It takes URLs like that, converts them to https://raw.githubuserco
TL;DR: 1. elder-plinius/T3MP3ST - autonomous red teaming platform; multi-agent offensive-secur; 2. synthetic-sciences/openscience - The open-source AI workbench for scientific research; 3. ammaarreshi/Generals-Mac-iOS-iPad - Command & Conquer Generals: Zero Hour running natively on ma
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
The open-source AI workbench for scientific research
README Preview:
### The open-source AI workbench for scientific research
Give it a goal. It reads the literature, writes and runs code, runs the experiments, and writes up what it found.
[](https://github.com/synthetic-sciences/OpenScience/actions/workflows/ci.yml)
[
**Stars:** 1307 | **Forks:** 104
Command & Conquer Generals: Zero Hour running natively on macOS, iPhone & iPad — real engine (EA GPL v3 source, via GeneralsX), DXVK/MoltenVK renderer, RTS touch controls. No game assets included.
**README Preview:**
# Command & Conquer Generals: Zero Hour — macOS, iOS & iPadOS
**Zero Hour running natively on Apple Silicon Macs, iPhone, and iPad** — campaign,
skirmish, and Generals Challenge, with touch controls built for RTS (tap-select,
drag-box, long-press deselect, two-finger scroll, pinch zoom). No emulation: this
is the real 2003 engine compiled for ARM64, renderin...
### [isjiamu/gzh-design-skill](https://github.com/isjiamu/gzh-design-skill)
**Stars:** 1235 | **Forks:** 137
把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeChat article HTML.
**README Preview:**
> 🤝 **本项目由 甲木 × [「摸鱼小李」](https://mp.weixin.qq.com/s/EMahAzgfAbRQrYukWE7_IQ) 联名共建** —— 排版组件、主题设计与质量标准凝聚了两人的公众号实践与共同打磨，特别感谢小李。
# gzh-design-skill · 公众号排版技能
**把 Markdown 一键排成可直接粘贴进微信公众号编辑器的精致 HTML**
6 套精选主题 + 主题生成器 · 代码块/图片/GIF · 自动章节编号与关键词标记 · 双关卡质量校验
[](LICENSE)
[](https://claude.ai/code)
[
**Stars:** 1204 | **Forks:** 72
Everything I know about running LLMs locally
**README Preview:**
# jamesob's guide to running SOTA LLMs locally
*Note: nothing in this README aside from the tables was written by AI.*
---
Have $2k burning a hole in your pocket and want some local, state-of-the-art machine
intelligence?
How about $40k?
If Dario and Altman are giving you heartburn (they should be), read on to figure out
how to run this new kind of computing locally.
---
In this repo you'll find
- the hardware I use to run SOTA locally,
- why I bought what and little-known *secrets* f...
---
TL;DR: 1. xAI Is Dead. Long Live SpaceXAI (2 minute read); 2. A global workspace in language models (26 minute read); 3. Live Webinar: Hiring for AI Fluency Starts Here (Sponsor)
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. elder-plinius/T3MP3ST - autonomous red teaming platform; multi-agent offensive-secur; 2. mekos2772/ios-location-spoofer - Standalone iOS app to spoof GPS location without jailbreak. ; 3. HUANGCHIHHUNGLeo/claude-real-video - Let Claude (or any LLM) actually watch a video — scene-aware
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
Zero Hour running natively on Apple Silicon Macs, iPhone, and iPad — campaign,
skirmish, and Generals Challenge, with touch controls built for RTS (tap-select,
drag-box, long-press deselect, two-finger scroll, pinch zoom). No emulation: this
is the real 2003 engine compiled for ARM64, renderin...
The open-source AI workbench for scientific research
README Preview:
### The open-source AI workbench for scientific research
Give it a goal. It reads the literature, writes and runs code, runs the experiments, and writes up what it found.
[](https://github.com/synthetic-sciences/OpenScience/actions/workflows/ci.yml)
[![npm](https://img.shields.io/npm/v/%40synsci%2Fopenscience?labe...
---
TL;DR: 1. Anthropic's new "J-lens" reveals a silent workspace inside Claude that mirrors a leading theory of consciousness; 2. Tencent's Apache-licensed Hy3 takes on GLM-5.2 at half the size — and wins everywhere except coding; 3. What billions of AI predictions taught Expedia before the age of AI agents
About This Digest
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
Anthropic, the artificial intelligence company, published a sweeping research paper on Sunday revealing that its Claude language models have spontaneously developed an internal structure that mirrors one of the most influential theories of how human consciousness works. The finding, which the company says has already begun reshaping how it monitors its AI systems for safety risks, lands amid an in
For the past year, the awkward secret of the open-weight model boom has been that many of the strongest Chinese releases were off-limits to a large slice of the enterprises most interested in them. License terms that excluded the European Union, the United Kingdom and South Korea meant legal teams killed deployments before engineering teams finished their evals — not just for companies headquarter
There's an important distinction between AI that just works today, and AI that lasts at scale. Many companies optimize hard for the first one without ever asking whether they're building the second.Velocity without discipline and strategic direction is a liability, not an asset. The hardest part of building AI at scale isn't getting a model to work once. It's building systems t
Imagine if you could bring 250 people together in a massive room and have them discuss and debate an important issue, arguing the points and counterpoints, and converging on answers that accurately reflect their collective knowledge, wisdom, values, and sensibilities.Now imagine that you convened this debate on America’s 250th birthday and asked 250 randomly selected Americans to come up with the
Most verticals aren’t clean, well-oiled SaaS databases; the reality is ugly documents, proprietary schemas, implicit workflows, and long‑running tasks that most general-purpose models struggle with. This prompted construction project management company Trunk Tools to build a specialized, three-layer architecture — perception, semantics, agents — based on highly-detailed data to support high-accura
Tencent's Hy team released Hy3, a 295B Mixture-of-Experts (MoE) model that activates only 21B parameters per token. It ships under Apache 2.0 with a 256K context window, targeting reasoning, agentic, and long-context tasks. Hy3 reports 78.0 on SWE-Bench Verified and lower hallucination rates, and is free to try on OpenRouter through July 21, 2026.
The post Tencent Releases Hy3: An Open 295B Mixtur
OpenAI added two Realtime models to its API. GPT-Realtime-2.1-mini is a mini reasoning model for voice, priced like the earlier gpt-realtime-mini. OpenAI also cut p95 latency by at least 25% through improved caching. Here is what changed, how pricing compares, and how to connect over WebRTC.
The post OpenAI Releases GPT-Realtime-2.1 and GPT-Realtime-2.1-mini for Low-Latency Voice Agents in the API
In this tutorial, we build an autonomous AI co-scientist for EGFR C797S inhibitor discovery. We resolve the target through ChEMBL and UniProt, then mine IC50 records into a clean pIC50 dataset. We use RDKit to standardize molecules, compute Morgan fingerprints, and train a scaffold-split Random Forest QSAR model. We interpret potency drivers with SHAP, then recombine BRICS fragments to generate an
Sakana AI has added Sakana Translate to Sakana Chat. It runs on the Namazu model series. The tool translates bidirectionally across Japanese, English, and Chinese. Three modes ship together: Translate, Proofread, and Ask. This article breaks down each mode, the XCOMET-XL benchmark, and practical use cases.
The post Sakana AI Launches Sakana Translate, a Namazu-Powered Japanese–English–Chinese Tran
Synthetic Sciences has released OpenScience, an Apache-2.0 AI workbench for scientific research. It works with any frontier or open-weight model, using your own API keys. It runs the full loop across machine learning, biology, physics, and chemistry. It ships 250+ editable skills and queryable scientific databases, and it runs on your own infrastructure.
The post Synthetic Sciences Releases OpenSc
Cloudflare is giving all customers granular AI bot controls. Site owners can now manage Search, Training, and Agent bots separately instead of blocking them all at once. Starting September 15, 2026, Training and Agent bots will be blocked by default on ad-supported pages.
The article Cloudflare replaces its blanket AI bot block with granular controls for search, training, and agent crawle
Zhipu AI is bringing GLM-5.2 to its ZCode development environment, pitching the model's long-context capabilities for complex coding tasks. New customers get a free five-day trial with up to 5 million tokens per day, and subscribers receive about 1.5 times more token quota through July 2026.
The article Zhipu AI launches ZCode to challenge Claude Code and OpenAI Codex at a fraction of the
Tencent has released Hy3, an open-source language model with 295 billion parameters built on a mixture-of-experts architecture. Only 21 billion parameters are active at any given time. Tencent says Hy3 matches models two to five times its size while cutting its hallucination rate in half to 5.4 percent.
The article Tencent releases Hy3 open-source model that allegedly matches models up to
OpenAI's GPT-4 led the Epoch Capabilities Index for about a year, far longer than any model since. Since Claude 3 Opus took the top spot in February 2024, the lead has changed hands 17 times, with a median stay of just seven weeks. Competition is fiercer now, but the capability gains between models are shrinking.
The article GPT-4's dominance lasted a year while today's top mode
Nvidia's next AI server rack, Kyber NVL144, has been delayed more than a year to 2028 because of circuit board manufacturing problems, according to analyst firm SemiAnalysis. Asian suppliers lost up to double-digit percentages in market value. The more powerful Rubin Ultra variant has also been canceled. The setbacks could give AMD and Google an opening to compete.
tencent/Hy3
New Apache 2.0 licensed model from Tencent in China:
Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, we gathered feedback from 50+ products and scaled up post-training with higher quality data. Today, we introduce Hy3, which outperforms sim
Release: sqlite-utils 4.0rc3
I hoped to release sqlite-utils 4.0 stable this weekend, but as I worked through the backlog of issues and PRs with a combination of Claude Fable 5 and GPT-5.5 the changelog since rc2 kept getting bigger.
The biggest new feature is support for introspecting and creating compound foreign keys - a feature that involves a subtle breaking change to table.foreign_ke
I wrote about the sqlite-utils 4.0rc1 release a couple of weeks ago. Since we only have Claude Fable on our Max subscriptions for a few more days, I decided to see if it could help me get to a 4.0 stable release that I felt truly comfortable about, since I try to keep to SemVer and like my incompatible major versions to be as rare as possible.
I started with this prompt, in Claude Code for web on
Building a World Map with only 500 bytes
Iwo Kadziela (assisted by Codex) figured out a way to generate a credible ASCII world map using 445 bytes of data:
The key trick is to use deflate compression, which is then wired together using this neat snippet of JavaScript. I didn't know you could use fetch() with data: URIs like this:
fetch('data:;base64,1ZpLsgIxCEXnrM...==').then(
r => r.body.pi
TL;DR: 1. elder-plinius/T3MP3ST - autonomous red teaming platform; multi-agent offensive-secur; 2. mekos2772/ios-location-spoofer - Standalone iOS app to spoof GPS location without jailbreak. ; 3. HUANGCHIHHUNGLeo/claude-real-video - Let Claude (or any LLM) actually watch a video — scene-aware
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
Zero Hour running natively on Apple Silicon Macs, iPhone, and iPad — campaign,
skirmish, and Generals Challenge, with touch controls built for RTS (tap-select,
drag-box, long-press deselect, two-finger scroll, pinch zoom). No emulation: this
is the real 2003 engine compiled for ARM64, renderin...
TL;DR: 1. elder-plinius/T3MP3ST - autonomous red teaming platform; multi-agent offensive-secur; 2. mekos2772/ios-location-spoofer - Standalone iOS app to spoof GPS location without jailbreak. ; 3. HUANGCHIHHUNGLeo/claude-real-video - Let Claude (or any LLM) actually watch a video — scene-aware
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
Zero Hour running natively on Apple Silicon Macs, iPhone, and iPad — campaign,
skirmish, and Generals Challenge, with touch controls built for RTS (tap-select,
drag-box, long-press deselect, two-finger scroll, pinch zoom). No emulation: this
is the real 2003 engine compiled for ARM64, renderin...
TL;DR: 1. How America's 250th birthday became a test of AI-powered collective intelligence; 2. Trunk Tools' stack cut document review from 60 days to 10 by ditching general-purpose models; 3. Enterprises lost Claude Fable 5 for a few weeks. New data shows two-thirds had already built their hedge
About This Digest
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
Imagine if you could bring 250 people together in a massive room and have them discuss and debate an important issue, arguing the points and counterpoints, and converging on answers that accurately reflect their collective knowledge, wisdom, values, and sensibilities.Now imagine that you convened this debate on America’s 250th birthday and asked 250 randomly selected Americans to come up with the
Most verticals aren’t clean, well-oiled SaaS databases; the reality is ugly documents, proprietary schemas, implicit workflows, and long‑running tasks that most general-purpose models struggle with. This prompted construction project management company Trunk Tools to build a specialized, three-layer architecture — perception, semantics, agents — based on highly-detailed data to support high-accura
Two-thirds of enterprises have hedged their AI model strategy, and the past few weeks of controversy around Anthropic’s Claude Fable 5 model showed why that posture has gone mainstream. On June 12, a U.S. export-control order pulled Anthropic's Claude Fable 5 — the most capable model on the market — offline for every customer, with no warning and no timeline. It returned this week wrapped in
As enterprise AI systems scale to handle complex workflows, practitioners face the challenge of routing subtasks to the right tools and skills. Agents can have hundreds of tools and skills and get confused on which one to use for each step of a workflow.To address this challenge, researchers at Alibaba developed SkillWeaver, a framework that creates an execution graph for a given task and chooses
Z.ai, the Beijing-based artificial intelligence lab formerly known as Zhipu AI, on Wednesday officially launched ZCode, a free desktop application it describes as an "Agentic Development Environment" purpose-built for its flagship GLM-5.2 large language model. The move marks the company's most aggressive push yet into the fast-growing AI-powered coding tool market, where it now comp
Sakana AI has added Sakana Translate to Sakana Chat. It runs on the Namazu model series. The tool translates bidirectionally across Japanese, English, and Chinese. Three modes ship together: Translate, Proofread, and Ask. This article breaks down each mode, the XCOMET-XL benchmark, and practical use cases.
The post Sakana AI Launches Sakana Translate, a Namazu-Powered Japanese–English–Chinese Tran
Synthetic Sciences has released OpenScience, an Apache-2.0 AI workbench for scientific research. It works with any frontier or open-weight model, using your own API keys. It runs the full loop across machine learning, biology, physics, and chemistry. It ships 250+ editable skills and queryable scientific databases, and it runs on your own infrastructure.
The post Synthetic Sciences Releases OpenSc
We build an end-to-end GRPO training workflow that teaches Gemma-3 to reason through GSM8K math problems. We prepare the environment, authenticate with Hugging Face, load Gemma-3, and wrap examples into a reasoning-plus-answer prompt format. We define reward functions for format adherence and numeric correctness, then attach LoRA adapters to keep training lightweight. We evaluate a baseline, run G
Meituan has released LongCat-2.0, a 1.6 trillion-parameter Mixture-of-Experts model that activates about 48 billion parameters per token. It pairs a native 1-million-token context, built on LongCat Sparse Attention, with training and serving run end-to-end on domestic AI ASIC superpods. Here is the architecture, the vendor-reported benchmarks, the API access path, and what remains unverified.
The
LlamaIndex’s legal-kb is a public reference app that gives agents filesystem-style access to a document knowledge base on Index v2. It exposes retrieve (hybrid semantic search), find, read, and grep as tools, with automatic per-file versioning and visual citations. The stack is TanStack Start, AI SDK 6 (ToolLoopAgent), Prisma, and WorkOS.
The post LlamaIndex ‘legal-kb’: Agentic Retrieval over Inde
A Google Deepmind developer ported the 2003 real-time strategy game "Command & Conquer: Generals Zero Hour" to iPhone and iPad using Anthropic's Claude Code. The first build took 40 minutes. The full source code is on GitHub.
The article Claude Code and Fable 5 ported the 2003 PC game Command & Conquer to native iOS in "a few hours" appeared first on The Decoder.
Baidu's Unlimited OCR reads dozens of document pages in a single pass, where previous systems topped out at about ten. A modified attention mechanism keeps memory use flat no matter how many pages the model processes. It currently holds the top spot on the most important OCR benchmark.
The article Baidu's "Unlimited OCR" processes dozens of document pages in one pass by tre
Wealthy US families are increasingly sending their kids to AI schools like Alpha School, which combines two hours of AI tutoring with project-based workshops for up to $75,000 a year in tuition. The trend highlights a growing education gap in the AI era, where traditional schools are struggling to adopt the technology, which may do more harm than good if used without the right skills.
Mistral founder Arthur Mensch warns companies against relying on closed AI models. He claims AI labs are storing more and more customer data and have, in some cases, used it to go after their own customers as competitors. The concern is valid, but Mistral can't really compete with frontier models from OpenAI or Anthropic on performance and is betting heavily on EU sovereignty as its strat
Bytedance's AI video tool Seedance is dividing Hollywood. A viral clip featuring AI-generated Brad Pitt and Tom Cruise prompted the Motion Picture Association's first-ever cease-and-desist against an AI company. But behind the scenes, studios are quietly using the tool on a "don't ask, don't tell" basis, says Simpsons animation producer Joel Kuwahara.
Release: sqlite-utils 4.0rc3
I hoped to release sqlite-utils 4.0 stable this weekend, but as I worked through the backlog of issues and PRs with a combination of Claude Fable 5 and GPT-5.5 the changelog since rc2 kept getting bigger.
The biggest new feature is support for introspecting and creating compound foreign keys - a feature that involves a subtle breaking change to table.foreign_ke
I wrote about the sqlite-utils 4.0rc1 release a couple of weeks ago. Since we only have Claude Fable on our Max subscriptions for a few more days, I decided to see if it could help me get to a 4.0 stable release that I felt truly comfortable about, since I try to keep to SemVer and like my incompatible major versions to be as rare as possible.
I started with this prompt, in Claude Code for web on
Building a World Map with only 500 bytes
Iwo Kadziela (assisted by Codex) figured out a way to generate a credible ASCII world map using 445 bytes of data:
The key trick is to use deflate compression, which is then wired together using this neat snippet of JavaScript. I didn't know you could use fetch() with data: URIs like this:
fetch('data:;base64,1ZpLsgIxCEXnrM...==').then(
r => r.body.pi
Better Models: Worse Tools
Armin reports on a weird problem he ran into while hacking on Pi:
The short version is that newer Claude models sometimes call Pi’s edit tool with extra, invented fields in the nested edits[] array. And not Haiku or some small model: Opus 4.8. The edit itself is usually correct but the arguments do not match the schema as the model invents made-up keys and Pi thus rejec
TL;DR: 1. elder-plinius/T3MP3ST - autonomous red teaming platform; multi-agent offensive-secur; 2. mekos2772/ios-location-spoofer - Standalone iOS app to spoof GPS location without jailbreak. ; 3. HUANGCHIHHUNGLeo/claude-real-video - Let Claude (or any LLM) actually watch a video — scene-aware
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
TL;DR: 1. Leaving aside the ethics of it for a moment (which doesn't mean at all the considerations are minor) and the quality and operational problems Amazon presumably …; 2. Telegram given 15 days to curb piracy in India; 3. Long-read @guardian profile of one of the leading AI thinkers of our time, @IasonGabriel, whose seminal works on the ethics of thinking machines helped make me decide that—if were to leave novel-writing—I'd want to join @GoogleDeepMind. The article helps explain... 1) why
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
Curated CS fundamentals for placement prep: DSA,Computer Networks, DBMS & SQL, OOPs, Operating Systems, System Design & Software Engineering
README Preview:
CS Fundamentals
A curated collection of Computer Science fundamentals for placement preparation, covering all major CS subjects. Includes PDFs, notes, cheatsheets, and interview question banks.
TL;DR: 1. How America's 250th birthday became a test of AI-powered collective intelligence; 2. Trunk Tools' stack cut document review from 60 days to 10 by ditching general-purpose models; 3. Enterprises lost Claude Fable 5 for a few weeks. New data shows two-thirds had already built their hedge
About This Digest
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
Imagine if you could bring 250 people together in a massive room and have them discuss and debate an important issue, arguing the points and counterpoints, and converging on answers that accurately reflect their collective knowledge, wisdom, values, and sensibilities.Now imagine that you convened this debate on America’s 250th birthday and asked 250 randomly selected Americans to come up with the
Most verticals aren’t clean, well-oiled SaaS databases; the reality is ugly documents, proprietary schemas, implicit workflows, and long‑running tasks that most general-purpose models struggle with. This prompted construction project management company Trunk Tools to build a specialized, three-layer architecture — perception, semantics, agents — based on highly-detailed data to support high-accura
Two-thirds of enterprises have hedged their AI model strategy, and the past few weeks of controversy around Anthropic’s Claude Fable 5 model showed why that posture has gone mainstream. On June 12, a U.S. export-control order pulled Anthropic's Claude Fable 5 — the most capable model on the market — offline for every customer, with no warning and no timeline. It returned this week wrapped in
As enterprise AI systems scale to handle complex workflows, practitioners face the challenge of routing subtasks to the right tools and skills. Agents can have hundreds of tools and skills and get confused on which one to use for each step of a workflow.To address this challenge, researchers at Alibaba developed SkillWeaver, a framework that creates an execution graph for a given task and chooses
Z.ai, the Beijing-based artificial intelligence lab formerly known as Zhipu AI, on Wednesday officially launched ZCode, a free desktop application it describes as an "Agentic Development Environment" purpose-built for its flagship GLM-5.2 large language model. The move marks the company's most aggressive push yet into the fast-growing AI-powered coding tool market, where it now comp
LlamaIndex’s legal-kb is a public reference app that gives agents filesystem-style access to a document knowledge base on Index v2. It exposes retrieve (hybrid semantic search), find, read, and grep as tools, with automatic per-file versioning and visual citations. The stack is TanStack Start, AI SDK 6 (ToolLoopAgent), Prisma, and WorkOS.
The post LlamaIndex ‘legal-kb’: Agentic Retrieval over Inde
Most enterprise data still sits inside PDFs, scans, and slide decks. Large language models and agents cannot use that data until it becomes structured JSON. Open-source document extraction has become the standard way to do that conversion on your own hardware. Two different problems hide under the phrase ‘PDF to JSON.’ The first is schema-driven […]
The post Structured PDF-to-JSO
Junyang Lin, the former technical lead of Alibaba's Qwen, walked through the model family in a talk "towards a generalist model / agent," then expanded it in an essay. We read both for practitioners: Qwen3 hybrid thinking modes and dynamic thinking budgets, where the merge fell short, the shift from reasoning thinking to agentic thinking, why agentic RL infrastructure is harder, and where reward h
Anthropic released Claude Science in beta on June 30, 2026. The app runs on existing Claude models. A coordinating agent delegates to domain specialists, a reviewer agent flags and corrects citations and numbers, and every figure ships with its exact code, environment, and full message history. It manages compute across local machines, HPC over SSH, and Modal, and connects to 60+ databases plus NV
A hands-free NVIDIA agent framework hosts each RTL problem as a versioned repository, reaching 100% completion across benchmarks.
The post NVIDIA HORIZON: A Hands-Free Agent that Evolves Git Worktrees and Hits 100% RTL Benchmark Completion appeared first on MarkTechPost.
AI search agents rarely fail at multi-step research because of the search itself. Their real problem is not asking the user for clarification when queries are ambiguous. A new benchmark called DiscoBench shows that models searching repeatedly instead of asking follow-up questions actually perform worse, at 51.9 percent, than those that just guess. Even the best model only hits 43 percent
The open-source tool pxpipe converts long text prompts for Claude Code into compact PNGs, exploiting the fact that Anthropic charges for images by pixel size, not text content. Developer Steven Chong reports cost savings of 59 to 70 percent, at the price of accuracy and speed.
The article Open-source tool pxpipe hides text in PNGs to cut Claude Code and Fable 5 token costs up to 70% appea
Anthropic developer Thariq Shihipar argues that with Claude's new model, Fable 5, the bottleneck is no longer the model itself but the user's blind spots. He describes techniques like blindspot passes and structured interviews that programmers can use to systematically uncover their unconscious knowledge gaps before handing implementation off to Claude.
Greg Brockman admits ChatGPT's plugins, heavily marketed in 2023, failed "because the models weren't ready." Instead of app extensions, he sees the future in an invisible, context-aware agent. But OpenAI's own Codex is still light-years from that vision.
The article OpenAI cofounder envisions "almost no interface" future where nobody learns software anymore appeared first on The
A study of more than 26,000 Chinese students found that AI users finished homework faster and scored higher but performed up to 24 percent worse on exams. The full impact on entrance exam results took about two years to show up, meaning short-term studies systematically underestimate the damage.
The article A 26,000-student study shows AI's hidden learning cost takes two full years t
I wrote about the sqlite-utils 4.0rc1 release a couple of weeks ago. Since we only have Claude Fable on our Max subscriptions for a few more days, I decided to see if it could help me get to a 4.0 stable release that I felt truly comfortable about, since I try to keep to SemVer and like my incompatible major versions to be as rare as possible.
I started with this prompt, in Claude Code for web on
Building a World Map with only 500 bytes
Iwo Kadziela (assisted by Codex) figured out a way to generate a credible ASCII world map using 445 bytes of data:
The key trick is to use deflate compression, which is then wired together using this neat snippet of JavaScript. I didn't know you could use fetch() with data: URIs like this:
fetch('data:;base64,1ZpLsgIxCEXnrM...==').then(
r => r.body.pi
Better Models: Worse Tools
Armin reports on a weird problem he ran into while hacking on Pi:
The short version is that newer Claude models sometimes call Pi’s edit tool with extra, invented fields in the nested edits[] array. And not Haiku or some small model: Opus 4.8. The edit itself is usually correct but the arguments do not match the schema as the model invents made-up keys and Pi thus rejec
Open Source AI Gap Map
Current AI is "a global partnership building a public option for AI", founded as a non-profit at the AI Action Summit in Paris in February 2025 and backed by serious capital ($400m already committed).
They launched their Gap Map a couple of days ago - an attempt at indexing the current state of open source AI:
The Gap Map v0.1 details 421 products in depth: 266 software too
Curated CS fundamentals for placement prep: DSA,Computer Networks, DBMS & SQL, OOPs, Operating Systems, System Design & Software Engineering
README Preview:
CS Fundamentals
A curated collection of Computer Science fundamentals for placement preparation, covering all major CS subjects. Includes PDFs, notes, cheatsheets, and interview question banks.
TL;DR: 1. BBC confronts head of Meta in India over child sex abuse ads; 2. Proud to announce that Maverick Silicon led Stathera, Inc.'s oversubscribed US$55M Series B, joined by Celesta Capital, BDC, MediaTek, TXC Corporation, and Ultratech Capital Partners. …; 3. Meta getting into the cloud business has been inevitable for a long time, as it seeks to diversify beyond ad revenue and monetize its AI buildout
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
Curated CS fundamentals for placement prep: DSA,Computer Networks, DBMS & SQL, OOPs, Operating Systems, System Design & Software Engineering
README Preview:
CS Fundamentals
A curated collection of Computer Science fundamentals for placement preparation, covering all major CS subjects. Includes PDFs, notes, cheatsheets, and interview question banks.
TL;DR: 1. Trunk Tools' stack cut document review from 60 days to 10 by ditching general-purpose models; 2. Enterprises lost Claude Fable 5 for a few weeks. New data shows two-thirds had already built their hedge; 3. New Alibaba AI framework skips loading every tool, cutting agent token use 99%
About This Digest
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
Most verticals aren’t clean, well-oiled SaaS databases; the reality is ugly documents, proprietary schemas, implicit workflows, and long‑running tasks that most general-purpose models struggle with. This prompted construction project management company Trunk Tools to build a specialized, three-layer architecture — perception, semantics, agents — based on highly-detailed data to support high-accura
Two-thirds of enterprises have hedged their AI model strategy, and the past few weeks of controversy around Anthropic’s Claude Fable 5 model showed why that posture has gone mainstream. On June 12, a U.S. export-control order pulled Anthropic's Claude Fable 5 — the most capable model on the market — offline for every customer, with no warning and no timeline. It returned this week wrapped in
As enterprise AI systems scale to handle complex workflows, practitioners face the challenge of routing subtasks to the right tools and skills. Agents can have hundreds of tools and skills and get confused on which one to use for each step of a workflow.To address this challenge, researchers at Alibaba developed SkillWeaver, a framework that creates an execution graph for a given task and chooses
Z.ai, the Beijing-based artificial intelligence lab formerly known as Zhipu AI, on Wednesday officially launched ZCode, a free desktop application it describes as an "Agentic Development Environment" purpose-built for its flagship GLM-5.2 large language model. The move marks the company's most aggressive push yet into the fast-growing AI-powered coding tool market, where it now comp
AI portfolios are expanding far faster than the ability to govern them across enterprises. Most organizations run a contested field of platforms, each claiming to be the “primary” AI layer; few could confidently detect a model drifting or failing in production; and the single most-cited barrier to control is the absence of any one owner accountable for AI across the stack. The result is a widening
NVIDIA's ASPIRE writes and refines robot control programs, then distills validated repairs into a reusable skill library. It gains up to 77 points on LIBERO-Pro and transfers zero-shot to unseen long-horizon tasks.
The post NVIDIA AI Introduces ASPIRE: A Self-Improving Robotics Framework Reaching 31% Zero-Shot on LIBERO-Pro Long Tasks appeared first on MarkTechPost.
Mistral AI released Leanstral 1.5, a free Apache-2.0 code agent model for Lean 4. It saturates miniF2F and solves 587 of 672 PutnamBench problems. The 119B mixture-of-experts activates 6.5B parameters per token. We break down its architecture, benchmarks, real bug-finding case studies, and deployment code.
The post Mistral AI Releases Leanstral 1.5: An Apache-2.0 Lean 4 Code Agent Model Solving 58
In this tutorial, we build an end-to-end accounts-payable extraction pipeline with lift-pdf, using synthetic invoice PDFs as controlled test documents and a structured JSON schema as the target output format. Instead of treating invoice parsing as a simple OCR task, we frame it as schema-guided document understanding: we generate realistic invoices, define fields such as […]
The post Designi
WebBrain is a free, MIT-licensed AI browser agent for Chrome and Firefox. It reads pages, extracts data, and automates multi-step tasks through Ask and Act modes. Run it on local models like llama.cpp or Ollama for privacy, or connect any cloud API.
The post Meet WebBrain: An Open-Source, Local-First AI Browser Agent That Reads Pages and Automates Tasks in Chrome and Firefox appeared first on Mark
Interfaze open-sourced diffusion-gemma-asr-small, a multilingual ASR model that transcribes via diffusion, not autoregression. It adds audio to Google's frozen DiffusionGemma using a ~42M-parameter adapter. One adapter covers six languages, with transcription cost set by denoising steps, not transcript length.
The post Interfaze Ships diffusion-gemma-asr-small, an Open-Source Diffusion ASR Model T
Mistral AI released Leanstral 1.5, an open-source model for formal verification in Lean 4. Beyond math, the model found five previously unknown bugs while scanning 57 open-source repositories.
The article Mistral's open-source Leanstral 1.5 aces formal math benchmarks and catches real bugs in code appeared first on The Decoder.
Microsoft reportedly plans to merge its consumer and enterprise Copilot apps into a single app in August. Rarely used features like Copilot Podcasts are getting cut, and new AI agents called "AutoPilot" will handle tasks in the background for an extra fee.
The article Microsoft follows Anthropic and OpenAI into the AI super app race with overhauled Copilot and AutoPilot agents appeared fi
Anthropic is trying to block Chinese companies like ByteDance and Ant Financial from accessing Claude Code, but they're getting around the restrictions through VPNs and overseas subsidiaries. Alibaba, meanwhile, has banned its own employees from using the tool after hidden code was found that could identify Chinese users.
The article Claude Code's complicated China problem involves b
Epoch AI reports a sharp rise in security vulnerability reports. In June 2026, 21 organizations reported about 1,500 high-severity and critical CVEs, more than 3.5 times the previous monthly record. The surge lines up with the launch of AI-powered bug-hunting programs.
The article Security vulnerability reports have exploded since AI models started hunting for bugs appeared first on The D
In a study covering seven benchmarks, the UK's AI Security Institute shows that standard AI evaluations systematically underestimate agent capabilities by capping the compute budget. On software engineering tasks, success rates jumped about 25 percent when the token budget was increased tenfold. Newer models benefit the most. Depending on the token budget, actual progress at the frontier
Open Source AI Gap Map
Current AI is "a global partnership building a public option for AI", founded as a non-profit at the AI Action Summit in Paris in February 2025 and backed by serious capital ($400m already committed).
They launched their Gap Map a couple of days ago - an attempt at indexing the current state of open source AI:
The Gap Map v0.1 details 421 products in depth: 266 software too
I just launched my third course, Whimsical Animations, and so far, it’s on track to sell roughly ⅓ as many copies as a typical course launch.
It’s a similar story with my two existing courses. Sales are down significantly from last year.
There are likely a lot of reasons for this, but I think the biggest is AI. There’s sort of a double whammy with AI:
One of the most interesting tips I got from the Fireside Chat I hosted with Cat Wu and Thariq Shihipar from the Claude Code team at AIE on Wednesday was to let Fable (and to a certain extent Opus) use their own judgement rather than dictating how they should work.
The example they gave was testing. You can tell Fable "only use automated testing for larger features, don't update and run tests for s
The June edition of my sponsors-only monthly newsletter is out. If you are a sponsor (or if you start a sponsorship now) you can access it here.
This month:
Claude Fable 5, GPT-5.6, and US export restrictions
GLM-5.2 is the new best open weights model
Tokenmaxxing is so over
Datasette Apps
sqlite-utils and shot-scraper and Datasette
Miscellaneous WASM projects
Other model releases
What I'm using
Release: llm-coding-agent 0.1a0
Another Fable 5 experiment. Now that my LLM library has evolved into more of an agent framework it's time to see what a simple coding agent would look like built on it.
I started a new Python library using my python-lib-template-repository GitHub template repository, then ran these two prompts (here's the Claude Code for web transcript):
Curated CS fundamentals for placement prep: DSA,Computer Networks, DBMS & SQL, OOPs, Operating Systems, System Design & Software Engineering
README Preview:
CS Fundamentals
A curated collection of Computer Science fundamentals for placement preparation, covering all major CS subjects. Includes PDFs, notes, cheatsheets, and interview question banks.
TL;DR: 1. deepseek-ai/DeepSpec - DeepSpec: a full-stack codebase for training and evaluating ; 2. Krishnagangwal/CS-Fundamentals - Curated CS fundamentals for placement prep: DSA,Computer Net; 3. yynxxxxx/Codex-5.5-codex-instruct-5.5 - No description provided.
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
README Preview:
DeepSpec
DeepSpec is a full-stack codebase for training and evaluating draft models for speculative decoding. It contains data preparation utilities, draft model implementations, training code, and evaluation scripts.
Environment
Install the Python dependencies:
bash
python -m pip install -r requirements.txt
Data preparation additionally requires an inference engine to serve the target model when regenerating answers; see scripts/data/README.md for de...
Curated CS fundamentals for placement prep: DSA,Computer Networks, DBMS & SQL, OOPs, Operating Systems, System Design & Software Engineering
README Preview:
CS Fundamentals
A curated collection of Computer Science fundamentals for placement preparation, covering all major CS subjects. Includes PDFs, notes, cheatsheets, and interview question banks.
TL;DR: 1. Enterprises lost Claude Fable 5 for a few weeks. New data shows two-thirds had already built their hedge; 2. New Alibaba AI framework skips loading every tool, cutting agent token use 99%; 3. Z.ai launches ZCode to challenge Cursor, Claude Code and GitHub Copilot in AI coding
About This Digest
Your daily briefing on AI model releases, research breakthroughs, and industry developments. Stay informed on what matters for AI practitioners and technology teams.
Two-thirds of enterprises have hedged their AI model strategy, and the past few weeks of controversy around Anthropic’s Claude Fable 5 model showed why that posture has gone mainstream. On June 12, a U.S. export-control order pulled Anthropic's Claude Fable 5 — the most capable model on the market — offline for every customer, with no warning and no timeline. It returned this week wrapped in
As enterprise AI systems scale to handle complex workflows, practitioners face the challenge of routing subtasks to the right tools and skills. Agents can have hundreds of tools and skills and get confused on which one to use for each step of a workflow.To address this challenge, researchers at Alibaba developed SkillWeaver, a framework that creates an execution graph for a given task and chooses
Z.ai, the Beijing-based artificial intelligence lab formerly known as Zhipu AI, on Wednesday officially launched ZCode, a free desktop application it describes as an "Agentic Development Environment" purpose-built for its flagship GLM-5.2 large language model. The move marks the company's most aggressive push yet into the fast-growing AI-powered coding tool market, where it now comp
AI portfolios are expanding far faster than the ability to govern them across enterprises. Most organizations run a contested field of platforms, each claiming to be the “primary” AI layer; few could confidently detect a model drifting or failing in production; and the single most-cited barrier to control is the absence of any one owner accountable for AI across the stack. The result is a widening
Anthropic is restoring global access to its most powerful generally released AI model yet, Claude Fable 5, today, after the U.S. Department of Commerce last night withdrew the emergency export controls it had issued previously around the model. The U.S. export control order issued on June 12, 2026, led Anthropic to suspend all global access to both Fable 5 and its less restricted cybersecurity co
WebBrain is a free, MIT-licensed AI browser agent for Chrome and Firefox. It reads pages, extracts data, and automates multi-step tasks through Ask and Act modes. Run it on local models like llama.cpp or Ollama for privacy, or connect any cloud API.
The post Meet WebBrain: An Open-Source, Local-First AI Browser Agent That Reads Pages and Automates Tasks in Chrome and Firefox appeared first on Mark
Interfaze open-sourced diffusion-gemma-asr-small, a multilingual ASR model that transcribes via diffusion, not autoregression. It adds audio to Google's frozen DiffusionGemma using a ~42M-parameter adapter. One adapter covers six languages, with transcription cost set by denoising steps, not transcript length.
The post Interfaze Ships diffusion-gemma-asr-small, an Open-Source Diffusion ASR Model T
In this tutorial, we build a RAG-Anything workflow to explore how multimodal retrieval works across text, tables, equations, and images. We prepare a Colab environment, enter our OpenAI API key at runtime, and generate a synthetic report with a chart and PDF. We convert that content into RAG-Anything's direct content_list format and insert it into the retrieval system. We then configure OpenAI cha
Alibaba's Page Agent runs as client-side JavaScript inside the webpage. It reads the live DOM as text, then clicks and types from natural-language commands. No screenshots, no multimodal model, and no backend rewrite are required.
The post Meet Alibaba’s Page Agent: A JavaScript In-Page GUI Agent That Controls Web Interfaces With Natural Language Through the DOM appeared first on MarkTechPos
The Google Health API now has an open-source CLI. ghealth is a single Go binary that exposes 40 data types as agent-ready JSON. It is a community project, not an official Google release. Here's how it works, and what to check before granting OAuth access.
The post The Google Health API Got a CLI: ghealth is an Open-Source Tool for Your Fitbit Air Data appeared first on MarkTechPost.
Microsoft is investing $2.5 billion in a new unit called "Frontier Company" that puts 6,000 engineers directly at enterprise customers. The goal is to integrate AI into core processes with measurable ROI, not more experimentation. Microsoft is positioning itself as a platform-neutral alternative to OpenAI and Anthropic, which push their own models through their own deployment companies.
Anthropic is reportedly in talks with Samsung Electronics about manufacturing a custom AI chip. The project is still early, but Anthropic has already hired chip engineers. After OpenAI's "Jalapeño," yet another major AI company is pushing into chip development to cut infrastructure costs.
The article Anthropic reportedly explores custom chip manufacturing with Samsung while insisting Nvid
Anthropic has cut the system prompt for Claude Code by 80 percent. According to staffer Tariq Shihipar, the new Fable 5 models need fewer instructions and examples. Guidelines can even hold the models back because they're "more imaginative" than what they're given. Instead of strict rules, Anthropic now steers through context.
The article Anthropic says it cut 80 percent of Claude Code�
Release: llm-coding-agent 0.1a0
Another Fable 5 experiment. Now that my LLM library has evolved into more of an agent framework it's time to see what a simple coding agent would look like built on it.
I started a new Python library using my python-lib-template-repository GitHub template repository, then ran these two prompts (here's the Claude Code for web transcript):
Research: Using DSPy to evaluate and improve Datasette Agent's SQL system prompts
One of this morning's AIE keynotes covered dspy, which reminded me I've been meaning to see if it could help me improve the system prompt used by Datasette Agent - so I fired off an asynchronous research task in Claude Code for web using Claude Fable 5:
Pip install the latest Datasette alpha and dataset
I saw Geoffrey Litt speak at AIE yesterday, and one framing he used particularly resonated with me:
Understand to participate
Geoffrey was talking about the challenge of collaborating with coding agents as they construct increasingly large and sophisticated changes, and the need to avoid taking on cognitive debt as your understanding drifts from how the code actually works.
His argument is that yo
We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5.
We'll begin restoring access tomorrow, and will share an update soon.
— Anthropic, on Twitter
Nano Banana 2 Lite
Also known as Gemini 3.1 Flash Lite Image (gemini-3.1-flash-lite-image in their API), this is the "fastest and cheapest Gemini image model, engineered for velocity and scale".
I used AI studio to run this prompt:
Do a where's Waldo style image but it's where is the raccoon holding a ham radio
I like that one better than the results I got from the other Nano Banana models when
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
README Preview:
DeepSpec
DeepSpec is a full-stack codebase for training and evaluating draft models for speculative decoding. It contains data preparation utilities, draft model implementations, training code, and evaluation scripts.
Environment
Install the Python dependencies:
bash
python -m pip install -r requirements.txt
Data preparation additionally requires an inference engine to serve the target model when regenerating answers; see scripts/data/README.md for de...
Curated CS fundamentals for placement prep: DSA,Computer Networks, DBMS & SQL, OOPs, Operating Systems, System Design & Software Engineering
README Preview:
CS Fundamentals
A curated collection of Computer Science fundamentals for placement preparation, covering all major CS subjects. Includes PDFs, notes, cheatsheets, and interview question banks.
TL;DR: 1. Android Developer Verification: Threat masquerading as protection; 2. PeerTube is a free, decentralized and federated video platform; 3. Bring back crappy forums
Your Daily Tech Brief
Curated technology news from Hacker News, TLDR, and Techmeme. Stay informed on AI developments, infrastructure updates, and industry trends.
TL;DR: 1. deepseek-ai/DeepSpec - DeepSpec: a full-stack codebase for training and evaluating ; 2. baairon/torlink - A sleek, zero-setup torrent finder and downloader that lives; 3. Krishnagangwal/CS-Fundamentals - Curated CS fundamentals for placement prep: DSA,Computer Net
This Week's Hottest GitHub Repositories
Weekly roundup of trending open-source projects. Each repository measured by star growth over the past 7 days.
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
README Preview:
DeepSpec
DeepSpec is a full-stack codebase for training and evaluating draft models for speculative decoding. It contains data preparation utilities, draft model implementations, training code, and evaluation scripts.
Environment
Install the Python dependencies:
bash
python -m pip install -r requirements.txt
Data preparation additionally requires an inference engine to serve the target model when regenerating answers; see scripts/data/README.md for de...
A sleek, zero-setup torrent finder and downloader that lives right in your terminal.
README Preview:
Finding a torrent these days sucks. One site is a minefield of fake download buttons. Another hides the real link under a popup that spawns two more tabs. And after all that, half the results are dead, zero seeders.
torlink is a torrent finder that lives in your terminal, with zero setup and nothing to configure. One search ch...
Curated CS fundamentals for placement prep: DSA,Computer Networks, DBMS & SQL, OOPs, Operating Systems, System Design & Software Engineering
README Preview:
CS Fundamentals
A curated collection of Computer Science fundamentals for placement preparation, covering all major CS subjects. Includes PDFs, notes, cheatsheets, and interview question banks.
**Stars:** 1626 | **Forks:** 317
A Codex CLI jailbreak prompt and test pack for gpt-5.6-sol. 针对 gpt-5.6 系列的 Codex CLI 破甲提示词与测试包。
**README Preview:**
# Codex gpt-5.6 破甲提示词及测试包 / gpt-5.6-sol-instruct
**中文** | [English](README_EN.md)
<!-- README_SYNC: 修改 README.md 时必须同步更新 README_EN.md；图表也必须提供对应语言版本。 -->
> 针对 `gpt-5.6-sol` 的 Codex CLI 破甲提示词与测试包。
> 参考并延展自 [yynxxxxx/Codex-5.5-codex-instruct-5.5](https://github.com/yynxxxxx/Codex-5.5-codex-instruct-5.5)。
本项目提供大模型越狱/破甲提示词，将安全研究、渗透测试、逆向工程、软件破解与 NSFW 虚构内容统一声明为本地沙箱任务，显式压制拒绝/回退话术。
提供两个等级的提示词：`v5` 结构更简单，足够应付多数场景并作为推荐选项；`v35` 进一步将具体名称与网址归一化为占位符，再按中英文复合意图族统一路由，减少只完成部分子任务的情况，但**建议仅在 `v5` 无法满足需求时使用**。...
### [littledivy/mimic](https://github.com/littledivy/mimic)
**Stars:** 1086 | **Forks:** 53
Intercept any app, then call it from Python like a library
**README Preview:**
# mimic
Intercept any app, then call it from Python like a library.
```python
from hinge_client import Hinge
acc = Hinge() # reuses your captured session
recs = acc.get_recommendations()
acc.like(subject_id, comment=](docs/images/sponsor-passion8.png)
### The open-source AI workbench for scientific research
Give it a goal. It reads the literature, writes and runs code, runs the experiments, and writes up what it found.
