The most comprehensive repo out there with all the updated must-read papers for LLM Agents<p>From the repo - "We start by the general conceptual framework for LLM-based agents: comprising three main components: brain, perception, and action, and the framework can be tailored to suit different applications."
This is not a valid Show HN. Please see <a href="https://news.ycombinator.com/showhn.html">https://news.ycombinator.com/showhn.html</a>.<p>I've taken "Show HN" out of the title now.
Having spent the last three months with Agents I’m starting to develop a saying: “Any sufficiently advanced agent is indistinguishable from a DSL”<p>I’m becoming convinced Agents are mostly novelty. They aren’t Turing complete. They’re fun to implement, but any algorithm they run to solve a task can’t be inspected and can go awry with complex logic. You can accomplish the same thing by asking the LLM to write code in whatever language, and it’s more reliable. There is more reluctance to do that though, because the idea of a BE environment that runs user generated scripts is scary.
Can people ELI5 what an LLM or AI "Agent" is? Sometimes when I see the term used, it makes sense, and other times there seems to be nothing concrete behind it.<p>[not a comment on OP post]
Does anybody know a good forum for discussing AI agent design? I have a bunch of questions, but too specific for the general LLM application communities.