Is the "AI Agent" hype making our apps worse?

Chat & Discussions AI / LLMs
2

Evidence

Prefer concrete evidence over guesswork.

https://github.com/openai/codex/blob/31648563c8d7f77957c79cc04501d0ed11844635/codex-rs/core/src/guardian/policy.md

1 Like
Any first-hand experience with Claude model getting "nerfed" down after using it for a while?