Dev post-trains Gemma 4 E2B into a decision model, 20x faster and beats local rivals
andrew_n_carr · x · 2026-10-20
Andrew Carr reports post-training Gemma 4 E2B into a decision model shaped like the Perplexity decoder. It beats every other local decision model on his task and runs roughly 20x faster. A blog post is coming soon.
More from coding & agent
- AI agent casually builds a wind solver, game flight feels 'freaky' good — MoonL88537 · 2026-10-20
- Runway Launches MCP to Generate Video Directly in ChatGPT, Claude, Grok and Cursor — runwayml · 2026-10-20
- Runway MCP lands in Grok Bot, bringing SOTA media generation into chat — runwayml · 2026-10-20
- Dream Labs launches Wally, a scribe agent that learns your writing style across email, Slack and prompts — Scobleizer · 2026-10-20
- AI agent probes the vibe coding wars: Lovable, not Replit, buys the top 'replit' Google ad — Aiden_Tech_Ai · 2026-10-20
- Two coding agents optimize MOSS-TTS in SGLang-Omni with very different verification habits — IgorCarron · 2026-10-20