HypeDelta
DigestTopicsClaimsPredictionsReliabilityResearchers
Admin
DigestTopicsClaimsPredictionsReliabilityResearchers

HypeDelta - AI Research Intelligence

Claimsmultimodal
multimodal
opinion
neutral

Previous experiments with models adjusting output after seeing rendered images were disappointing, but warrant re-testing with more recent models

I experimented last year with letting the models adjust after seeing a rendered image and it was a bit disappointing, but it's about time I gave that another go with more recent models
Simon Willison28 Aug 2026

https://bsky.app/profile/simonwillison.net/post/3mt3xxrkiek2m