Toby Ord: image models are like a lossy compression format for photos
tobyordoxford · x · 2026-09-09
Oxford researcher Toby Ord responds to a discussion on how much information a photograph contains: he doubts a model could reproduce a photo it has never seen, since the prompt carries too little information. He likens image models to a compressed image format that can't reproduce all the noise in a photo — part of a broader exchange on whether prompt information content can define artistic contribution.
Related event: Oxford scholar: a photo holds ~42 bytes of info, so is AI art art?(3 posts)→
More from Models
- DeepSeek reportedly running four V4 model versions, user says culling is coming to cut inference costs — teortaxesTex · 2026-09-09
- DeepSeek Accused of Silently Swapping Models Behind Its API, Sparking Debate — teortaxesTex · 2026-09-09
- Dev complains about over-blocking safety filters, asks Sam Altman for compute on Collatz — mertdumenci · 2026-09-09
- Dev claims turning off thinking mode makes AI models 5x faster, urges default non-thinking modes — Daniel_Farinax · 2026-09-09
- Yoav Goldberg: OpenAI's "cannot rule out" user data use is a lawyered admission — MannyKayy · 2026-09-09
- Heavy user on Astra: beats a junior hire on cost, but still fumbles simple tasks — RachelVT42 · 2026-09-09