# "“I am an AI Safety Researcher”" by Ashe Vazquez Nuñez Page: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/i-am-an-ai-safety-researcher-by-ashe-vazquez-nu-ez Text version: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/i-am-an-ai-safety-researcher-by-ashe-vazquez-nu-ez.md Podcast: [LessWrong (Curated & Popular)](https://stenobird.com/podcast/lesswrong-curated-popular-5643401) Published: 2026-09-25T08:45:21+00:00 Episode link: https://www.buzzsprout.com/2037297/episodes/19862399-i-am-an-ai-safety-researcher-by-ashe-vazquez-nunez.mp3 Audio file: https://www.buzzsprout.com/2037297/episodes/19862399-i-am-an-ai-safety-researcher-by-ashe-vazquez-nunez.mp3 Processing state: not_requested JSON: https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/i-am-an-ai-safety-researcher-by-ashe-vazquez-nu-ez Duration seconds: 1664 ## Resource Written as part of the MATS 9.1 extension program, mentored by Richard Ngo. Additional thanks to Andrew Wu, Maria Kostylew, and Lennie Wells for helpful draft feedback and editing. This post reflects on the tortured distinction between "safety" and "capabilities" in AI research. Richard Ngo has written about why the alignment vs. capabilities ontology is conceptually fraught, and is currently arguing that key strategic decision-makers in and around "AI safety" have brought about the AI ... ## Actions - request_transcript: `POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/i-am-an-ai-safety-researcher-by-ashe-vazquez-nu-ez/transcription-requests` — Idempotently request low-priority transcript generation for this episode. - read_markdown: `GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/i-am-an-ai-safety-researcher-by-ashe-vazquez-nu-ez.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.