Episode
"Astra is much better at reasoning with filler tokens than previous models" by Dylan Xu, SebastianP, Alek Westover
- Published
- Sep 12, 2026
- Duration seconds
- 933
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/astra-is-much-better-at-reasoning-with-filler-tokens-than-previous-models-by-dylan-xu-sebastianp-alek-westover/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/astra-is-much-better-at-reasoning-with-filler-tokens-than-previous-models-by-dylan-xu-sebastianp-alek-westover.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
We measure GPT-6-Astra's capabilities when its prompt is padded with a variable number of meaningless “filler” tokens (e.g., dots) and it is told to answer immediately without reasoning. On tasks designed to require lots of serial cognition, Astra performs significantly better with filler tokens than without (e.g., improving from ~10% to ~50% on 4-hop natural facts reasoning). On more general benchmarks, filler tokens also modestly improve Astra's performance (e.g., improving from ~60% to ~9...