at://
/
app.bsky.feed.post
/
3mno3m5lim22s
sign in
All
4
Record
2
Post
1
PostEmbed
1
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
but how about this? arxiv.org/abs/2505.17120
4d
We have only limited understanding of how and why large language models (LLMs) respond in the ways that they do. Their neural networks have proven challenging to interpret, and we are only beginning t...
arxiv.org
Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions
hakwan lau
LLM introspection revisited. if we do the controls properly we may not have strong enough evidence just yet arxiv.org/html/2605.26...
4d
arxiv.org
Can LLMs Introspect? A Reality Check
hakwan lau
