Allie the Icon
17 posts

Allie the Icon
@allietheicon
Doing iconic shit DevRel at @TypesafeAI Queer as fuck


can ai agents invent writing on their own? recent pet project: 2 agents share a world but each sees only half. their only communication: 7×7 pixel glyphs. they develop symbols, build theories of meaning, and evaluate their own writing. no convergence yet but fascinating to watch!


Telling an AI model that it’s an expert programmer makes it a worse programmer go.theregister.com/feed/www.there…

The plan for Obsidian is to never grow beyond 10-12 people, never take VC funding, never collect personal data or analytics. Continue building with the assumption that software is ephemeral, files matter more than apps. Use formats that are open and durable. See our manifesto:




LiteLLM HAS BEEN COMPROMISED, DO NOT UPDATE. We just discovered that LiteLLM pypi release 1.82.8. It has been compromised, it contains litellm_init.pth with base64 encoded instructions to send all the credentials it can find to remote server + self-replicate. link below





Giving a new roommate a copy of every key you own (house, car, safe, storage shed) on day one would seem crazy. Unfortunately, that's what most people do with their AI agents ( @openclaw etc) by default. @AllieTheIcon and I broke down AI security vs. safety in a 2-hour chat on @designertom's Discord. Allie had some great analogies that Higgins then made into a Remotion video. Let me know if the full 10 page summarization doc would be of interest to folks from the convo!




