pull down to refresh

ChatGPT 'got absolutely wrecked' by Atari 2600 in beginner's chess matchwww.tomshardware.com/tech-industry/artificial-intelligence/chatgpt-got-absolutely-wrecked-by-atari-2600-in-beginners-chess-match-openais-newest-model-bamboozled-by-1970s-logic
184 sats \ 1 comment \ @0xbitcoiner 9 Jun gaming
OpenAI's latest and greatest AI model was outclassed by the 1.19 MHz near 50-year-old console gaming legend.
In a quite unexpected turn of events, it is claimed that OpenAI’s ChatGPT “got absolutely wrecked on the beginner level” while playing Atari Chess. Citrix Architecture and Delivery specialist, Robert Jr. Caruso, discovered this gameplay skill anomaly over the weekend. Caruso pitted the 1979 Atari Chess title, played within an emulator for the 1977 Atari 2600 console gaming system, against the might of ChatGPT 4o.
...read more at tomshardware.com
write
preview
related posts
36 sats \ 0 replies \ @SimpleStacker 9 Jun
I don't think 4o is the right model for attempting this. 4o is their fast text generation model which I think is more prone to hallucination.
reply