@no_stp_on_snek: very cool. GLM seems to be like, nah we good.
Summary
A tweet showcases a visualization of 8 LLMs' reasoning traces on a probability question, highlighting moments of self-correction and pivoting.
View Cached Full Text
Cached at: 07/06/26, 04:08 PM
very cool. GLM seems to be like, nah we good.
stevibe (@stevibe): You know that “But, wait…” moment in every LLM thinking trace?
I made it visible.
I asked 8 models the same tricky probability question and rendered their reasoning as trees. Every time a model rejects its own idea and pivots, every “But…”, every “Wait, actually…”, a new
Similar Articles
@stevibe: You know that "But, wait..." moment in every LLM thinking trace? I made it visible. I asked 8 models the same tricky pr…
A visualization that shows how 8 different LLMs reason through a tricky probability question, with branches representing moments of self-correction like 'But, wait...'.
@lateinteraction: very cool work !!
Guowei Xu discusses limitations of Best-of-N and tree search methods for LLMs on hard reasoning problems, noting sparse verification signals and that candidates remain within the model's distribution.
LLMs know when they are wrong. I made a fix relating to Anthropic's new "global workspace" paper [R]
The author presents a method to make LLMs verbalize calibrated confidence by using a linear probe on mid-layer states and a small trained bridge to confidence logits, requiring only 200 labeled examples and no weight modification. This is linked to Anthropic's global workspace paper explaining the know-say gap.
@techNmak: I finally found someone who explained why LLM inference is fundamentally different from regular inference… without over…
A tweet shares a link to a clear, accessible explanation of why LLM inference differs from traditional inference, presented in a casual walking video.
@stevibe: Which LLMs actually love to think? Tested 7 models on 5 math problems, measured reasoning length. The think winners: bo…
Benchmarked 7 LLMs on 5 math problems; Qwen3.5 27B and 35B A3B generated the longest reasoning chains, exceeding 10k tokens per question.