Topic

AI Game Development

3 stories

ModelsAnalysis
Bijan Bowen says Claude Haiku 5.5 has pretty insane capability; tests used 1% of weekly usage
Bowen said the testing used 1% of weekly usage; the first skate game beat GPT-6 Luna’s, and its revision came close to state of the art from about six months earlier.
Models DeskOct 7
ModelsAnalysis
How Claude Sonnet 5.5 trounced GPT-6.1 Sol in Bijan Bowen’s four-task review
Bijan Bowen found Sonnet’s Perry branding exceptionally strong and its music-and-video result significantly better than Sol’s, driving their decisive overall preference.
Oct 2
ModelsAnalysis
Bijan Bowen says Claude Sonnet 5.5 demolishes GPT-6 Sol on visual tasks
Bowen calls Sonnet 5.5 a monster, judging its GTA-style game better than pricier Claude Opus 5.5’s after visual tests they said put it far ahead of GPT-6 Sol.
Oct 2