HNGlance

Top Best New Show

Reading Between the Dots: Decoding Hidden Computation Across Filler Tokens

https://arxiv.org/abs/2607.03502

by user_7832 • 4 days ago

2 2 4 days ago

AR

Related Stories

Loading related stories...

Comments

2

user_78322• 4 days ago

(To quote one of the authors)

If you ask a frontier LLM a multi-hop reasoning question, e.g., "Who won the Nobel Prize for Chemistry in (1900 + Mozart's age when he died)?", it usually can't answer correctly immediately (no thinking)

BUT if you ask the same question & append 300 dots, suddenly it can answer? (Because the LLM starts thinking "during" the dots).

user_78322• 4 days ago

Tweet: https://x.com/kaleybrauer/status/2078185882926846044

https://xcancel.com/kaleybrauer/status/2078185882926846044

Explanatory image:

https://x.com/kaleybrauer/status/2078185882926846044/photo/1

Source preview

arxiv.org

HNGlance

© 2024-2026 HN Glance. Story content belongs to its original sources.

Privacy
Terms