{"podcast":{"title":"Training Data","slug":"training-data","podcast_index_feed_id":null,"rss_url":"https://feeds.megaphone.fm/trainingdata","website_url":"https://www.sequoiacap.com/","image_url":"https://megaphone.imgix.net/podcasts/8ca8a61c-08b4-11ef-97ab-9fe273d59030/image/4a16fd33b06708003827556209cd42b7.png?ixlib=rails-4.3.1&max-w=3000&max-h=3000&fit=crop&auto=format,compress","author":"Sequoia Capital","episode_count":104,"summary":"Join us as we train our neural nets on the theme of the century: AI. Sonya Huang, Pat Grady and more Sequoia Capital partners host conversations with leading AI builders and researchers to ask critical questions and develop a deeper understanding of the evolving technologies—and their implications for technology, business and society. The content of this podcast does not constitute investment advice, an offer to provide investment advisory services, or an offer to sell or solicitation of an offer to buy an interest in any investment fund.","last_synced_at":"2026-08-02T15:06:49.231983+00:00","page_url":"https://stenobird.com/podcast/training-data"},"episode":{"title":"How Cursor Trained Composer on Fireworks: Distributed Infrastructure for High-Performance RL","slug":"how-cursor-trained-composer-on-fireworks-distributed-infrastructure-for-high-performance-rl","published_at":"2026-05-26T09:00:00+00:00","page_url":"https://stenobird.com/podcast/training-data/how-cursor-trained-composer-on-fireworks-distributed-infrastructure-for-high-performance-rl","show_page_url":"https://stenobird.com/podcast/training-data","url":"https://pscrb.fm/rss/p/traffic.megaphone.fm/CPUAI1086513324.mp3","audio_url":"https://pscrb.fm/rss/p/traffic.megaphone.fm/CPUAI1086513324.mp3","summary":"Cursor's Federico Cassano and Fireworks' Dmytro Dzhulgakov explain how they collaborated to build Composer as a specialized foundation model. The core insight: models have finite capacity in their weights, and allocating all those bits to the singular task of software engineering in Cursor frees the model to be both better at the task and far more efficient at inference. Rather than start from pre-training and work up, they took an unconventional top-down approach — mid-training and RL on top of an open-source base to get a useful model into users' hands fast, then specializing the model around real Cursor usage. With Fireworks providing distributed infrastructure, Composer delivers frontier-class coding performance with the speed of a much smaller model. Hosted by Sonya Huang, Sequoia Capital","meta_description":"Cursor's Federico Cassano and Fireworks' Dmytro Dzhulgakov explain how they collaborated to build Composer as a specialized foundation model. The core ins…","key_points":[],"chapters":[],"topics":[],"duration_seconds":2733,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/training-data/episodes/how-cursor-trained-composer-on-fireworks-distributed-infrastructure-for-high-performance-rl/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/training-data/how-cursor-trained-composer-on-fireworks-distributed-infrastructure-for-high-performance-rl.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}