TeortaxesTex: scale-optimized synthetic curricula could yield Opus-level cognitive core in 2B-active/30B models
teortaxesTex · x · 2026-11-21
Replying to a discussion about local small-model capability, X user teortaxesTex argues we are nowhere near the ceiling: incentives may be lacking to push to the max, but scale-optimized synthetic curricula are entering a regime where they work really well, and he thinks an Opus 5.5-level cognitive core in a 2B-active/30B-total model should be doable. This is a speculative take, not an official claim.
More from Models
- Microsoft's new models reportedly up to 80x cheaper and 50x faster — ChrisUniverse · 2026-11-22
- GPT-6.2 Astra writing success rate falls to 85.9% from 91.2% — arena · 2026-11-22
- GPT-6.2 Astra gains +50 in coding, drops -54 in chat on Agent Arena — arena · 2026-11-22
- Apple testing daily limits on advanced Siri AI requests in iOS 27.3 beta, per leak — alvelda · 2026-11-22
- Muse plays GTA6, suggesting guardrails don't cover game playing — Dave_Maynor · 2026-11-22
- Paying Google Workspace users locked out of Gemini over custom-domain account restrictions — film_girl · 2026-11-22