{"podcast":{"title":"The New Stack Podcast","slug":"the-new-stack-podcast-1092634","podcast_index_feed_id":1092634,"rss_url":"https://feeds.simplecast.com/IgzWks06","website_url":"https://thenewstack.simplecast.com","image_url":"https://image.simplecastcdn.com/images/1425ebfd-95bd-4a66-b963-a0b885c75680/bb688835-10e4-4197-b01f-34221ccb5d38/3000x3000/tns-makers-logo-simplecast.jpg?aid=rss_feed","author":"The New Stack Podcast","episode_count":300,"summary":"The New Stack Podcast is all about the developers, software engineers and operations people who build at-scale architectures that change the way we develop and deploy software. For more content from The New Stack, subscribe on YouTube at: https://www.youtube.com/c/TheNewStack","last_synced_at":"2026-07-08T06:18:52.955116+00:00","page_url":"https://stenobird.com/podcast/the-new-stack-podcast-1092634"},"episode":{"title":"What comes after attention? This startup says it already knows.","slug":"what-comes-after-attention-this-startup-says-it-already-knows","published_at":"2026-07-07T16:00:00+00:00","page_url":"https://stenobird.com/podcast/the-new-stack-podcast-1092634/what-comes-after-attention-this-startup-says-it-already-knows","show_page_url":"https://stenobird.com/podcast/the-new-stack-podcast-1092634","url":"https://thenewstack.simplecast.com/episodes/what-comes-after-attention-this-startup-says-it-already-knows-GdPLGPuE","audio_url":"https://cdn.simplecast.com/media/audio/transcoded/317e9dbc-9a52-4da7-9725-c4578874b757/5672b58f-7201-4e0e-b0af-da702259d97f/episodes/audio/group/0cce3fce-c6b4-4d62-9b41-fb5d77153deb/group-item/9d4e0931-5dc9-4dd9-8bbd-3caf785125b8/128_default_tc.mp3?aid=rss_feed&feed=IgzWks06","summary":"Subquadratic is beginning to back up its ambitious claims with benchmarks and third-party validation for its SubQ 1.1 Small model, which uses its proprietary Sparse Attention (SSA) architecture to dramatically improve long-context performance. Rather than comparing every token to every other token, SSA selectively processes relationships, enabling near-linear scaling while maintaining high accuracy across context windows of up to 12 million tokens. The company reports near-perfect retrieval performance, competitive coding and reasoning benchmarks, and compute savings of up to 1,000x at maximum context lengths.","meta_description":"Subquadratic is beginning to back up its ambitious claims with benchmarks and third-party validation for its SubQ 1.1 Small model, which uses its propriet…","key_points":[],"chapters":[],"topics":[],"duration_seconds":1219,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/the-new-stack-podcast-1092634/episodes/what-comes-after-attention-this-startup-says-it-already-knows/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/the-new-stack-podcast-1092634/what-comes-after-attention-this-startup-says-it-already-knows.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}