By the way in case anyone was curious: No, nothing crazy/weird happens if you give an LLM simulacrum an agent scaffold that credibly lets it plan and execute arbitrary code. It basically just does…

Posters: jd_pressman. jd_pressman

3 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/jd_pressman/status/1831771197723570292