{"podcast":{"title":"Boston Computation Club","slug":"boston-computation-club-4031660","podcast_index_feed_id":4031660,"rss_url":"https://anchor.fm/s/5eee01ac/podcast/rss","website_url":"https://podcasters.spotify.com/pod/show/bostoncc","image_url":"https://d3t3ozftmdmh3i.cloudfront.net/production/podcast_uploaded_nologo/15826563/15826563-1623263635731-99a8ec66007e4.jpg","author":"Max von Hippel","episode_count":89,"summary":"The Boston Computation Club is a small seminar group focused on mathematical computer science, and computational mathematics. Its name is plagiarized from the London Computation Club. Boston Computation Club meetings occur roughly every other week, on weekends, around 5pm EDT (modulo speaker availability). The usual format is a 20m presentation followed by 40m of discussion. Some, but not all, meetings are posted on YouTube and in podcast form.","last_synced_at":"2026-09-08T12:21:35.234206+00:00","page_url":"https://stenobird.com/podcast/boston-computation-club-4031660"},"episode":{"title":"2/17/26: Approximately Aligned Decoding with Daniel Melcer","slug":"2-17-26-approximately-aligned-decoding-with-daniel-melcer","published_at":"2026-02-18T03:47:26+00:00","page_url":"https://stenobird.com/podcast/boston-computation-club-4031660/2-17-26-approximately-aligned-decoding-with-daniel-melcer","show_page_url":"https://stenobird.com/podcast/boston-computation-club-4031660","url":"https://podcasters.spotify.com/pod/show/bostoncc/episodes/21726-Approximately-Aligned-Decoding-with-Daniel-Melcer-e3f81q5","audio_url":"https://anchor.fm/s/5eee01ac/podcast/play/115655941/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-1-18%2Ff585dd16-8419-3cad-5f6f-f7c172abecc5.m4a","summary":"Daniel Melcer is a PhD student at Northeastern University, where he researches formal methods, reinforcement learning, and large language models, among other things. Daniel also has the most colorful hair in the business (bright red for this talk, other colors for other occasions). Today he joined us to talk about some really exciting work he completed at Amazon, and to expand on his general vision of where constrained inference problems are heading in the future.","meta_description":"Daniel Melcer is a PhD student at Northeastern University, where he researches formal methods, reinforcement learning, and large language models, among ot…","key_points":[],"chapters":[],"topics":[],"duration_seconds":2939,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/boston-computation-club-4031660/episodes/2-17-26-approximately-aligned-decoding-with-daniel-melcer/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/boston-computation-club-4031660/2-17-26-approximately-aligned-decoding-with-daniel-melcer.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}