LLM post-training
Nous Releases Arete-27B to Alter Qwen’s Political Framing
Nous releases Arete-27B, a Qwen3.8-27B fine-tune targeting Chinese-state framing. Its bias and capability results come from Nous’s own tests.
Latest
No posts to display
Timeline
Every story in LLM post-training, grouped by month.
November 2026
- 8 Nov 2026: Nous Releases Arete-27B to Alter Qwen’s Political FramingNous releases Arete-27B, a Qwen3.8-27B fine-tune targeting Chinese-state framing. Its bias and capability results come from Nous’s own tests.
October 2026
- 29 Oct 2026: Particle-1 Coding Model Uses About 45% Fewer Tokens, Particle SaysSuhail Doshi's Particle has launched Particle-1, a DeepSeek V4.1 Flash coding model it says uses about 45% fewer tokens with similar accuracy.
- 23 Oct 2026: Moonshot's Own Tests Put Kimi K3.1 Pro at 65.7% on Terminal-BenchMoonshot AI's Kimi K3.1 Pro is live with a 1M-token context. Its own tests put it near Claude Opus 5.5 on coding; open weights…
- 19 Oct 2026: Together AI Lets Teams Write Their Own RL Loops on Open ModelsTogether AI launches Together Post-Training for custom RL and SFT on open models, at $9 per B200 GPU-hour for eight weeks. Customer quotes are…
- 7 Oct 2026: NVIDIA's LoGRA Cuts RL Training Memory With Low-Rank Gradient SketchesNVIDIA’s LoGRA paper shows low-rank gradient sketches cutting average RL training memory by up to 45.7% on tested Qwen reasoning setups—and making 27B RL…
Related stories
Latest from topics connected to LLM post-training. See all with connected topics
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.
