Mechanistic interpretability researchers applying causality theory to LLMs
1–10 of 101 posts
Re: Mechanistic interpretability researchers applying causality theory to LLMs
#2[stub for offtopicness] [[All: please don't post shallow-generic reactions to baity titles. Those are basically the same thing, a la https://en.wikipedia.org/wiki/Rubin_vase , and we're trying for something more substantive here.]]
Do they ?
Re: Mechanistic interpretability researchers applying causality theory to LLMs
#3[stub for offtopicness] [[All: please don't post shallow-generic reactions to baity titles. Those are basically the same thing, a la https://en.wikipedia.org/wiki/Rubin_vase , and we're trying for something more substantive here.]]
Do LLMs have Qualia?
Re: Mechanistic interpretability researchers applying causality theory to LLMs
#4[stub for offtopicness] [[All: please don't post shallow-generic reactions to baity titles. Those are basically the same thing, a la https://en.wikipedia.org/wiki/Rubin_vase , and we're trying for something more substantive here.]]
Do they ?
Of course they do, how else do you think they manage to implement new features in large codebases, or to prove new theorems? But you don't even have to assume they do because of the results- you can read their chain of thought.
Re: Mechanistic interpretability researchers applying causality theory to LLMs
#5[stub for offtopicness] [[All: please don't post shallow-generic reactions to baity titles. Those are basically the same thing, a la https://en.wikipedia.org/wiki/Rubin_vase , and we're trying for something more substantive here.]]
Do they ?
The article answers this question, at least to the extent it can be answered, at this time.
We see some signs of reasoning, but also we understand little about how they work.
Re: Mechanistic interpretability researchers applying causality theory to LLMs
#6[stub for offtopicness] [[All: please don't post shallow-generic reactions to baity titles. Those are basically the same thing, a la https://en.wikipedia.org/wiki/Rubin_vase , and we're trying for something more substantive here.]]
Do they ?
Yes, there is an LLM feature that we have anthropomorphized as "reasoning" or "thinking", where an LLM has a scratch space where it can dump tokens that help to improve the final output.
Re: Mechanistic interpretability researchers applying causality theory to LLMs
#7Earlier quoted context omitted.
Do they ?
The article answers this question, at least to the extent it can be answered, at this time. We see some signs of reasoning, but also we understand little about how they work.
Do we see actual signs of reasoning or is it anthropomorphism? We have an innate tendency to do so as humans.
Re: Mechanistic interpretability researchers applying causality theory to LLMs
#8[stub for offtopicness] [[All: please don't post shallow-generic reactions to baity titles. Those are basically the same thing, a la https://en.wikipedia.org/wiki/Rubin_vase , and we're trying for something more substantive here.]]
Clickbait article title.
The article body does not presume they reason.
Re: Mechanistic interpretability researchers applying causality theory to LLMs
#9Earlier quoted context omitted.
The article answers this question, at least to the extent it can be answered, at this time. We see some signs of reasoning, but also we understand little about how they work.
Do we see actual signs of reasoning or is it anthropomorphism? We have an innate tendency to do so as humans.
> Do we see signs of reasoning or is it anthropomorphism?
This is the part that so many folks just don't seem to understand (probably because it's been labeled as "thinking" or "reasoning" mode, and people assume that words have meaning). It's not reasoning or thought. It's spewing tokens pretending to "think", but it's actually just generating extra "context" to help the final answer be more coherent. The model isn't doing anything it doesn't already do. It's just doing more of it to improve the quality of the final answer displayed to the user.