dots3-note Preview: 280B Params, 512K Context for Long-Horizon Tasks
mhdfaran · x · 2026-08-29
rednote AI lab released dots3-note Preview, designed for long-running tasks where user needs evolve and conditions keep changing.
Specs:
- 280B total parameters, 16B active
- 512K context length
- Text + Vision + Audio
The model targets real-world scenarios lacking clean instructions or fixed goals, adapting to dynamic variables like budget and flight changes during trip planning.
More from Models
- Image Decision Benchmark JevImageBench hits v0.3.0 with reshuffled Top 5 — airesearch12 · 2026-10-16
- Forecast: Meta's Muse Spark Open May Become the Best Non-Chinese Open-Weight LLM on Agentic Benchmarks — zsakib_ · 2026-10-16
- Claude Opus 5.5 effort levels tested: low reasoning iterates 9x faster than max — tom_doerr · 2026-10-16
- Matt Turck podcast unpacks Jev: TypeSafe's machine-native AI and its RLHF critique — mattturck · 2026-10-16
- LoOPSD: looping a model's own layers as teacher lifts Qwen3-1.7B GSM8K from 42% to 80% — burny_tech · 2026-10-16
- JevBench adds synced dual-chart view for capability, cost and speed tradeoffs — airesearch12 · 2026-10-16