Perplexity's decision model wins Catan tournament at under half a cent per game
denisyarats · x · 2026-10-18
Perplexity's decision model won a Catan tournament, taking all 6 winning moves it was offered and finishing the final ahead despite being robbed 32 times by opponent Luna — all at under half a cent per game, making it the cheapest model in the field. Perplexity researcher denisyarats shared the result.
More from Fun
- Claude Opus simulates a user explaining Opus to itself, then breaks in with an 'inner-er voice' — repligate · 2026-10-18
- Dev's Claude stats: 818 sessions, 44.6B tokens, Opus 5.5 as favorite model — CtrlAltDwayne · 2026-10-18
- AI agent politely asks for permission to solve CAPTCHAs on your behalf — pbbakkum · 2026-10-18
- Dev builds a fully ASCII MMORPG — entire world rendered in colored text characters — HanchungLee · 2026-10-18
- Game devs clash with Tim Sweeney over AI code: 'unreadable code could kill Fortnite' — almmaasoglu · 2026-10-18
- You Can Pinpoint the Exact Moment Each AI Lab Started Vibecoding Its Product — MillionInt · 2026-10-18