# "Astra is much better at reasoning with filler tokens than previous models" by Dylan Xu, SebastianP, Alek Westover

Page: 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
Text version: 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
Podcast: [LessWrong (Curated & Popular)](https://stenobird.com/podcast/lesswrong-curated-popular-5643401)
Published: 2026-09-12T13:45:21+00:00
Episode link: https://www.buzzsprout.com/2037297/episodes/19793932-astra-is-much-better-at-reasoning-with-filler-tokens-than-previous-models-by-dylan-xu-sebastianp-alek-westover.mp3
Audio file: https://www.buzzsprout.com/2037297/episodes/19793932-astra-is-much-better-at-reasoning-with-filler-tokens-than-previous-models-by-dylan-xu-sebastianp-alek-westover.mp3
Processing state: not_requested
JSON: 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
Duration seconds: 933

## Resource

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...

## Actions

- request_transcript: `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.
- read_markdown: `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.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.