DID YOU KNOW THE #1 GITHUB TRENDING REPO (146K+ STARS) IS LITERALLY JUST A CLAUDE MD FILE? It uses @karpathy
's 4 LLM principles to keep AI in check: → Seek clarity: Always ask before making assumptions.
→ Stay minimal: Avoid bloat and keep things simple.
→ Edit
@datachaz
-
Claude MD File: Top GitHub Repo Uses Karpathy’s 4 LLM Principles for AI Control
By
–
-
Free AI Engineering Curriculum with 435 Lessons
By
–
this guy literally put a full AI engineering curriculum on GitHub and made it 100% FREE 435 lessons. 20 phases. 320 hours. The rule that makes this curriculum completely different: Every algorithm gets implemented from raw math before a single framework gets imported.
-
Solo founder raises $30M for AI company Polsia with zero employees
By
–
Be like Ben Cera.
— Charly Wargnier (@DataChaz) 22 mai 2026
> a solo founder who just raised $30M at a $250M valuation
> he built Polsia, an AI that can run your whole company, ENTIRELY alone
> it’s already at $10M ARR with ZERO employees
…the AI even pitched the VCs itself 🤯
UNREAL execution https://t.co/7YOGMUJRXv pic.twitter.com/Cyomlq9hvCBe like Ben Cera. > a solo founder who just raised $30M at a $250M valuation
> he built Polsia, an AI that can run your whole company, ENTIRELY alone
> it’s already at $10M ARR with ZERO employees …the AI even pitched the VCs itself UNREAL execution -
Check out the new Airtable agent platform by @howietl and the team!
By
–
when @howietl and the great minds behind @airtable ship a new agent platform, you don't scroll past. Test it out here → https://
hyperagent.com -
Addy Osmani’s Agent Skills: 19 Engineering Skills and 7 Commands
By
–
ICYMI, @addyosmani from Google recently dropped his new Agent Skills and it's pretty incredible. It brings 19 engineering skills + 7 commands to AI coding agents, all inspired by Google best practices AI coding agents are powerful, but left alone, they take shortcuts.
-
Stanford’s 9-part AI series: The gold standard for core fundamentals, starting with Transformers.
By
–
Forget the noise. If you want a solid foundation in AI, this 9-part @Stanford series is still one the gold standards. Just the core fundamentals explained by the people who teach this for a living. Lecture 1 – Transformer:
→ https://
youtube.com/watch?v=Q86qzJ
1K1Ss
… Lecture 2 – -
User review of AI vibe-coding platforms Base44 and Lovable
By
–
i’ve tried a bazillion vibe-coding platforms. Base44 and Lovable and currently my top 2. So yep, pretty stoked about this one. → https://
base44.com -
OpenHuman v0.54 Released with Autonomous Agent Workflows
By
–
Holy cow. OpenHuman v0.54 is ABSOLUTELY STACKED Autonomous Agent Todo boards Multi-step background workflows Major cross-platform stability & security updates 100+ bug fixes Best part? It's 100% open source. ace work from the @tinyhumansai team! repo in ↓
-
Using AI agents for proactive security auditing
By
–
TL;DR: The winner won't be the loudest AI, but the team turning threat expertise into active auditing agents. 360 shows static code review is no longer enough. Full report → https://
vul.360.net/archives/750 -
AI security splits as OpenClaw finds 23 vulns via live runtime testing
By
–
Meanwhile, 360 just found 23 vulns in OpenClaw by testing live runtime decisions. Is AI security splitting into 2 industries? Static code review is great. BUT auditing autonomous agents that read web data and trigger live actions is a TOTALLY different level of difficulty.