Post

2 pieces of content on the topic of LLM powered agents that I'd recommend: - The latest Latent Space episode by @swyx.io with @simon.fedi.simonwillison.net.ap.brid.gy - highly recommend! - The GoEX research paper. Late to the party on this one but the contents of it is more and more relevant today

Both of them bring up a crucial topic in terms of LLM powered agents: intermediate actions, and control over those intermediate actions. Do we want agents and LLMs to execute on our behalf, and if so, how do we do damage control if things go south.