Llms #074
A place to discuss llms—tips, questions, and real-world experience.
Sharing a resource related to llms 074.
Context: I'm working on llms 074 and ran into a decision point.
Question: What are common pitfalls when scaling AI agent safety?
Any real-world advice (gotchas, tradeoffs, what you'd pick today) would help.
Some notes on llms 074 based on recent work.
Checklist
If you’ve shipped something similar, what would you do differently?