# "Can activation verbalizers surface an internal chain of thought?" by oakhu, ryan_greenblatt Page: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/can-activation-verbalizers-surface-an-internal-chain-of-thought-by-oakhu-ryan-greenblatt Text version: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/can-activation-verbalizers-surface-an-internal-chain-of-thought-by-oakhu-ryan-greenblatt.md Podcast: [LessWrong (Curated & Popular)](https://stenobird.com/podcast/lesswrong-curated-popular-5643401) Published: 2026-06-22T06:58:17+00:00 Episode link: https://www.buzzsprout.com/2037297/episodes/19382397-can-activation-verbalizers-surface-an-internal-chain-of-thought-by-oakhu-ryan_greenblatt.mp3 Audio file: https://www.buzzsprout.com/2037297/episodes/19382397-can-activation-verbalizers-surface-an-internal-chain-of-thought-by-oakhu-ryan_greenblatt.mp3 Processing state: not_requested JSON: https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/can-activation-verbalizers-surface-an-internal-chain-of-thought-by-oakhu-ryan-greenblatt Duration seconds: 4778 ## Resource We introduce an evaluation for activation verbalizers: can they surface a target model's reasoning as it solves a math problem in a single forward pass? For open-weight NLAs, the answer seems to be: "possibly, but definitely not reliably". Lots of important capabilities currently require AI models to reason "out loud" in a natural-language chain of thought, which means that we can monitor important parts of their thinking. It would be nice to have this same affordance for the reasoning tha... ## Actions - request_transcript: `POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/can-activation-verbalizers-surface-an-internal-chain-of-thought-by-oakhu-ryan-greenblatt/transcription-requests` — Idempotently request low-priority transcript generation for this episode. - read_markdown: `GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/can-activation-verbalizers-surface-an-internal-chain-of-thought-by-oakhu-ryan-greenblatt.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.