Episode

What comes after attention? This startup says it already knows.

Podcast
The New Stack Podcast
Published
Jul 7, 2026
Duration seconds
1219
Processing state
not_requested
Canonical source
https://thenewstack.simplecast.com/episodes/what-comes-after-attention-this-startup-says-it-already-knows-GdPLGPuE
Audio
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
JSON
/v1/public/podcasts/the-new-stack-podcast-1092634/episodes/what-comes-after-attention-this-startup-says-it-already-knows
Markdown
/podcast/the-new-stack-podcast-1092634/what-comes-after-attention-this-startup-says-it-already-knows.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/the-new-stack-podcast-1092634/episodes/what-comes-after-attention-this-startup-says-it-already-knows/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/the-new-stack-podcast-1092634/what-comes-after-attention-this-startup-says-it-already-knows.md
    Read the agent-friendly Markdown representation of this episode resource.

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.