Teknium: models that train on only one harness can't be 'near AGI'
Teknium · x · 2026-09-07
- Teknium (Nous Research), in a discussion with pvncher, says models should simply be trained on multiple harnesses: every Chinese model, Fable, even Muse works across harnesses quite well.
- He argues it's hard to believe a lab is nearing AGI if its model can only be trained to handle one orchestration workflow—mocking the "era of AGI" narrative since Astra's release.
Related event: OpenAI Models Criticized for Overfitting to Native Harness(3 posts)→
More from Models
- Kimi K3.1 Pro regresses on Debate Benchmark while DeepSeek 1017 gains at lower cost — teortaxesTex · 2026-10-27
- 4 Hours of LLM Startup Research Produced a Convincing but Nonsense Product Thesis — annetgriffin · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- MiniMax matches Claude Opus 4.5 in non-benchmaxxed evals, users report — teortaxesTex · 2026-10-27
- Real-world math: GPT-6.1 Terra's half price is offset by 2-3x token usage, costing more than Sol — lordpuddingcup · 2026-10-27
- Fable 5.5 rumored to ship this week as partners still test — kimmonismus · 2026-10-27