Research
A little Ember-1 tl;dr. Seems like a great model! (Was recently asked on a podcast, given $ xx million, what's the best way to develop a fro…
A little Ember-1 tl;dr. Seems like a great model! (Was recently asked on a podcast, given $ xx million, what's the best way to develop a frontier LLM today? My recommendation was: start with an existi
A little Ember-1 tl;dr. Seems like a great model! (Was recently asked on a podcast, given $ xx million, what's the best way to develop a frontier LLM today? My recommendation was: start with an existing one and spend that budget on post-training. Great example here.) Ember-1 is hot on HN, our research team cooked it’s Kimi K3 post trained to be 40% more concise in reasoning same quality, 40% faster and cheaper
Related
- A lot of hype around OpenAI's Astra model here on my timeline today. Apparently, this goes back to a new article from The Information, which…
- Here's a link to the article: https://magazine.sebastianraschka.com/p/gpt-6-astra-looped-transformers-and
- Gated DeltaNet has been one of my favorite 'hybrid attention' newcomers in the good old transformer stack. Excited to see Gated DeltaNet-2. …
Source: Sebastian Raschka (X) | 2026-09-27