Weaviate Podcast: Persimmon uses real interaction data, not role-play, to model human behavior
CShorten30 · x · 2026-09-24
The Weaviate Podcast digs into what counts as human data when modeling how people actually behave. Persimmon's evaluation relies on real human interaction — including multi-party meeting transcripts and human tutoring conversations — rather than scripted exchanges.
Guests Alexis, Manya, and Niloofar explain why role-played dialogue represents a skewed distribution of behavior, and how Persimmon collects authentic interaction data for training and evaluation.
More from AGI Musings
- Could Opus 5.5 'solve' children's entertainment? The hyper-specialized content idea — repligate · 2026-09-24
- Musk: Human output is ~100 bits/sec while computers hit 1 trillion, hence Neuralink — XFreeze · 2026-09-24
- Only 2 of 46 AI Rollup Firms Get an A Grade: Vista and Apollo Top the Map — curious_vii · 2026-09-24
- Dario Amodei says Anthropic will 'slow down as much as necessary' to keep AI safe — Polymarket · 2026-09-24
- AI expert Dave Linthicum calls OpenAI doomsday narrative an overreaction — DavidLinthicum · 2026-09-24
- Altman at UN: some things AI builders say sound like bad sci-fi plots — ns123abc · 2026-09-24