AI agents that “self-reflect” perform better in changing environments
1–10 of 46 posts
Re: AI agents that “self-reflect” perform better in changing environments
#2So from this hacker news title I definitely thought it was saying that when you give some AI agents a self reflection like maybe by putting an internal monologue loop then they unlock an emergent animal-like exploration behavior.
But this is not what happened. Instead, some guys told AI agents to explore in the way that the guys think that animals explore. "Stanford researchers invented the “curious replay” training method based on studying mice to help AI agents"
Re: AI agents that “self-reflect” perform better in changing environments
#3Direct arxiv link:
https://arxiv.org/pdf/2306.15934.pdf
Re: AI agents that “self-reflect” perform better in changing environments
#4Exactly.
We keep leaving out 'motivation' on these models.
Since they are reacting to prompts.
But put them on a loop with goals and see what happens.
And, things like GPT are not 'embodied', since they don't live in the 'world' they can't associate language with physical reality. Put them in a simulated environment like a game, and it looks a lot more 'conscious'.
Re: AI agents that “self-reflect” perform better in changing environments
#5So from this hacker news title I definitely thought it was saying that when you give some AI agents a self reflection like maybe by putting an internal monologue loop then they unlock an emergent animal-like exploration behavior. But this is not what happened. Instead, some guys told AI agents to explore in the way that the guys think that animals explore. "Stanford researchers invented the “curious replay” training…
[dead]
Re: AI agents that “self-reflect” perform better in changing environments
#6The result is mildly interesting - improvement on an isolated task but none on the full benchmark - but what would be much more compelling is curiosity-driven replay in an LLM context combined with chain- or tree-of-thought techniques. This would be the machine analogy to noticing your confusion, a sort of "what do I need to know" or "what am I overlooking"? Anecdotally, language models perform better when you prompt them to ask their own questions in the process of answering yours, so I would expect curiosity to have a meaningful impact.
Re: AI agents that “self-reflect” perform better in changing environments
#7it's kind of interesting how increasingly frequently "stanford.edu" is finding its way into HN submissions, and did the increasing frequency start with the GPT-4 enthusiasm?
is that coincidence?
Re: AI agents that “self-reflect” perform better in changing environments
#8So from this hacker news title I definitely thought it was saying that when you give some AI agents a self reflection like maybe by putting an internal monologue loop then they unlock an emergent animal-like exploration behavior. But this is not what happened. Instead, some guys told AI agents to explore in the way that the guys think that animals explore. "Stanford researchers invented the “curious replay” training…
> Instead, some guys told AI agents to explore in the way that the guys think that animals explore.
Something, something, The Bitter Lesson.
Re: AI agents that “self-reflect” perform better in changing environments
#9So from this hacker news title I definitely thought it was saying that when you give some AI agents a self reflection like maybe by putting an internal monologue loop then they unlock an emergent animal-like exploration behavior. But this is not what happened. Instead, some guys told AI agents to explore in the way that the guys think that animals explore. "Stanford researchers invented the “curious replay” training…
I hate that titles can differ from the article here. It’s patronizing and commonly inaccurate or misleading.
Re: AI agents that “self-reflect” perform better in changing environments
#10So from this hacker news title I definitely thought it was saying that when you give some AI agents a self reflection like maybe by putting an internal monologue loop then they unlock an emergent animal-like exploration behavior. But this is not what happened. Instead, some guys told AI agents to explore in the way that the guys think that animals explore. "Stanford researchers invented the “curious replay” training…
[dead]