Albanie flags big jump in models' no-CoT task time horizon
SamuelAlbanie · x · 2026-09-04
DeepMind researcher Samuel Albanie shared a time-horizon evaluation chart and noted a "quite a big jump" in models' no-CoT (no chain-of-thought) time horizon — the length of tasks models can complete autonomously without reasoning steps — signaling another notable capability leap.
Related event: Researcher flags big jump in models' no-CoT time horizon(3 posts)→
More from Models
- Opus 5.5 tops OpenRouter spending in 20 of 29 task categories — mmurph · 2026-10-21
- Meta team builds open-source 30B LLM from scratch in months, hails 'second era' — TimDarcet · 2026-10-21
- DFlash drafter for Muse Glimmer-30B: 5 layers, blockwise 16-token spec decoding — TimDarcet · 2026-10-21
- EvoPress quantization shrinks 30B model from 56GB to 19GB at near-bf16 accuracy — TimDarcet · 2026-10-21
- Radar chart: Muse Glimmer-30B benchmarked against Gemma4-31B and Qwen3.6-27B — TimDarcet · 2026-10-21
- Privacy evals: Muse Glimmer-30B leaks less than Qwen3.6-27B on CIMemories — TimDarcet · 2026-10-21