This is a low information density blog post. I’ve really liked Zed’s blog posts in the past (especially about the editor internals!) so I hope this doesn’t come the wrong way, but this seems to be a loose restatement of what many people are empirically finding out by using LLM agents.

Perhaps good for someone just getting their feet wet with these computational objects, but not resolving or explaining things in a clear way, or highlighting trends in research and engineering that might point towards ways forward.

You also have a technical writing no no where you cite a rather precise and specific study with a paraphrase to support your claims … analogous to saying “Godel’s incompleteness theorem means _something something_ about the nature of consciousness”.

A phrase like: “Unfortunately, for now, they cannot (beyond a certain complexity) actually understand what is going on” referencing a precise study … is ambiguous and shoddy technical writing — what exactly does the author mean here? It’s vague.

I think it is even worse here because _the original study_ provides task-specific notions of complexity (a critique of the original study! Won’t different representations lead to different complexity scaling behavior? Of course! That’s what software engineering is all about: I need to think at different levels to control my exposure to complexity)