calle

gm

there's a different yet undiscovered type of AI psychosis that comes from managing 10 active coding agents at the same time

I'd take you!

assuming that's true, what can we learn from your mistakes?

The best part about this is dropping the link to your OpenClaw agent in your messenger and go on with your life

the crazy part is that @PABLOF7z litarally saw it all coming

made with clawi.ai 🦞 📝 1cb318a0…

sweet!

very good security audit group barghest found a cache poisoning bug in bitchat - responsible disclosure - submitted PR with patch - quick response and fast iterations - we made new friends (check them out, they rock) - invited them to a nostr conference - pure collaboration, sign of self-condifence - not little pathetic crying baby bitches like some "security research" larpers we've had the pleasure of interacting with in the past pleasure to work with professionals. https://barghest.asia/blog/bitchat-cache-poisoning/

very cool opengraph preview image by @ZEUS https://zeusln.com/e/cashuBpGFteCJodHRwczovL21pbnQubWluaW…

Google has open-sourced A2UI – a UI language for AI agents It allows agents generate user interfaces instead of only text. → Agents send a JSON description of UI components, and the client app renders them with its own trusted widgets. The benefits: - declarative UI format (JSON, not code) - safe: only approved components can be rendered - framework-agnostic (web, Flutter, etc.) - supports incremental UI updates So agents can "speak UI," while the application keeps control over security and implementation https://github.com/google/A2UI