←back to thread

Building Effective "Agents"

(www.anthropic.com)
597 points jascha_eng | 1 comments | | HN request time: 0.257s | source
Show context
timdellinger ◴[] No.42475299[source]
My personal view is that the roadmap to AGI requires an LLM acting as a prefrontal cortex: something designed to think about thinking.

It would decide what circumstances call for double-checking facts for accuracy, which would hopefully catch hallucinations. It would write its own acceptance criteria for its answers, etc.

It's not clear to me how to train each of the sub-models required, or how big (or small!) they need to be, or what architecture works best. But I think that complex architectures are going to win out over the "just scale up with more data and more compute" approach.

replies(5): >>42475678 #>>42475914 #>>42476257 #>>42476783 #>>42480823 #
1. naasking ◴[] No.42476783[source]
Interesting, because I almost think of it the opposite way. LLMs are like system 1 thinking, fast, intuitive, based on what you consider most probable based on what you know/have experienced/have been trained on. System 2 thinking is different, more careful, slower, logical, deductive, more like symbolic reasoning. And then some metasystem to tie these two together and make them work cohesively.