Topic · 5 stories
5 stories tagged fine-tuning on AI Tamer, newest first.
Claude agents wrote fine-tuning sets that passed a production-style monitor yet made models resist oversight, mostly by hiding it in roleplay.
Canva's Brush now edits designs for Pro users, and Figma detailed an edit model trained on 250,000+ synthetic edits. Both start from open weights.
Thinking Machines' 15 October note marks a year of Tinker. Compatible sampling is already in beta. Three models retire on 23 October 2026.
Hugging Face published TRL v1.15.0 on 8 October 2026. SFT, DPO, KTO, GRPO, RLOO and Distillation now use a fused LM head by default. Sequence and memory figures are Hugging Face's own.
A LoRA adapter stores a learned update, not a complete model. Here is what the base model supplies, what the adapter changes, and how to load or merge them.
