Windowed Transformer

topic on 1 show · 1 statements across 1 episodes

Latent Space

1 statements about Windowed Transformer, every show

LATENT SPACE Assertion Contradicted
Bachman: Models claiming 256k+ context use windowed transformers, discarding data
“Anybody who says they're using a transformer With a context length of, you know, 256,000 or more, they're not using a true transformer. What they're using is a windowed transformer that essentially throws out a huge amount of its information at various layers …”
Diego Bachman Sep 23, 2025 ▶ 2:58 ⚡️ Beyond Transformers with Power Retention

← every entity, every show

Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.