LLMs are terrible at designing AI systems
Summary
The author argues that while LLMs write ordinary programs with ease, they often take a roundabout route — building complex symbolic reasoning instead of simply calling another model — when designing systems that use LLMs themselves, and explores possible causes in training data and RL environments.
Why this matters
Covers LLM · Published within 6 hours
Source: Hacker News AI (hnrss) · www.seangoedecke.com