Alright!
I’m going to get some sleep, and in the morning, I’ll follow all the developers, founders, designers, and vibe-coders who leave a comment on this post and follow me!
Let's connect comunity!
May the Force be with you
🚨 Perplexity just open-sourced SPACE, an AI agent sandbox.
They stress-tested 9 frontier models with 118 escape & breach attempts from isolated containers. 0 succeeded.
Meanwhile, devs are literally passing raw sudo access to autonomous terminal agents in prod without a second thought.
Are we building the next generation of software, or just speedrunning the biggest cybersecurity disaster in history? 🧵👇
@IndependentEco the real problem is it's two separate brains. I hand tasks from Claude to Codex when one runs low, so neither plan goes to waste. still haven't found a way to complain about too much usage though
hey X 👋
looking to #connect with people who:
- live in Claude Code, Codex or Cursor all day
- build dev tools
- ship side projects with agents
- are building something solo from day 0
Say hi and let's connect 📷Building something?
what are you building? drop it below 👇
@AleksandrM37858 Мощный подход! Главное — случайно не стереть базу с "сотворения мира" 😄 Респект за свою архитектуру памяти на Postgres. Удачи в развитии агента!
The point isn't necessarily being able to explain the code—some people understand it perfectly well but simply can't put that understanding into words.
The real task is being able to verify what the AI has produced, spot any issues, and—if the AI happens to go offline—fix things yourself!