Humansand trains Persimmon and Ampersand with RLSF for proactive AI companionship
alexisjross · x · 2026-10-23
- Humansand builds Persimmon, a model designed to understand people — remembering what matters, knowing when to step in, and when to stay quiet.
- Its Ampersand model is trained with RLSF (Reinforcement Learning from Simulation Feedback) to improve these proactive judgment choices.
- The approach goes beyond Q&A toward proactive companionship and timing-aware assistance.
More from Models
- Sophont's Holon-S1 predicts genes and biomarkers from routine pathology slides — iScienceLuvr · 2026-10-23
- Doc parsing lite mode scores 75.1 vs Azure Read's 42.3 on OmniParseBench, dominates non-Latin scripts — VikParuchuri · 2026-10-23
- Datalab open-sources Indra OCR: a 1M-parameter model that beats PaddleOCR on CPU — VikParuchuri · 2026-10-23
- The inside story behind OpenAI's million-dollar math proof — scientificamerican · 2026-10-23
- Anthropic's anti-distillation defense cuts attacks 90-99%, but expert data is still for sale — johnkorrigan · 2026-10-23
- Hugging Face CEO open to reworking evals after researcher calls its benchmarks 'extremely problematic' — ClementDelangue · 2026-10-23