humans& releases &Tutor, a model trained to teach by learning against a learner model
gharik · x · 2026-10-31
humans& released &Tutor via its agent API — a model trained to teach. Its core method: train against Persimmon, a large-scale user model that plays the learner, rewarding the tutor by how much the student actually learns rather than answer correctness. The team designed evals showing how this changes tutoring behavior (diagnostic questioning, building on learner understanding) and validates Persimmon's learner modeling. &Tutor claims SOTA on TutorMoments, a benchmark built from real tutoring moments; API and model card are public.
Related event: Humans& Launches &Tutor: Model the Learner First, Then Train the AI Tutor(13 posts)→
More from Models
- Arena weekly: Gemini 4 Carbon tops Text Arena, GPT-6.1 Terra enters Agent Arena at #8 — arena · 2026-10-31
- 6 October models, same 5 trap-laden agent tasks: DeepSeek does it all for $0.02, hyped Flint passes 1/5 — latent_lurker8587 · 2026-10-31
- Security researcher: air-gapped AI agents are only possible with open-weight models — wunderwuzzi23 · 2026-10-31
- Gemini 4 Carbon tops Artificial Analysis index at 59, 23% cheaper per task than Opus 5.5 — rohanpaul_ai · 2026-10-31
- Podcast: Is Mistral Large 4 the West's best open model? Plus AI cyber threats — The Cognitive Revolution · 2026-10-31
- OpenAI shows GPT-6 Astra remotely controlling a robot arm in builder community — OpenAIDevs · 2026-10-31