←back to thread

Signs of introspection in large language models

(www.anthropic.com)
178 points themgt | 1 comments | 30 Oct 25 16:45 UTC | HN request time: 0s | source
Show context
andy99 ◴[31 Oct 25 22:47 UTC] No.45777552[source]▶
This was posted from another source yesterday, like similar work it’s anthropomorphizing ML models and describes an interesting behaviour but (because we literally know how LLMs work) nothing related to consciousness or sentience or thought.

My comment from yesterday - the questions might be answered in the current article: https://news.ycombinator.com/item?id=45765026

replies(3): >>45777598 #>>45780130 #>>45785998 #
1. ChadNauseam ◴[31 Oct 25 22:53 UTC] No.45777598[source]▶
> (because we literally know how LLMs work) nothing related to consciousness or sentience or thought.

1. Do we literally know how LLMs work? We know how cars work and that's why an automotive engineer can tell you what every piece of a car does, what will happen if you modify it, and what it will do in untested scenarios. But if you ask an ML engineer what a weight (or neuron, or layer) in an LLM does, or what would happen if you fiddled with the values, or what it will do in an untested scenario, they won't be able to tell you.

2. We don't know how consciousness, sentience, or thought works. So it's not clear how we would confidently say any particular discovery is unrelated to them.