News for hackers. Stuff that matters.
Re:Gemini "duck" demo was not done in realtime or with voice by jmathai on Thursday December 07, 2023 @03:26PM (#38561393)
> it rarely happens that it just finds stuff that's flat out wrong

"Flat out wrong" implies determinism. For answers which are deterministic such as "syntax checking" and "correctness of code" - this already happens.

ChatGPT, for example, will write and execute code. If the code has an error or returns the wrong result it will try a different approach. This is in production today (I use the paid version).

Re:Gemini "duck" demo was not done in realtime or with voice by bongodongobob on Thursday December 07, 2023 @04:00PM (#38561762)
Dollars to doughnuts says they are using GPT3.5.
Re:Gemini "duck" demo was not done in realtime or with voice by tomjakubowski on Thursday December 07, 2023 @04:13PM (#38561888)
I'm currently working with some relatively obscure but open source stuff (JupyterLite and Pyodide) and ChatGPT 4 confidently hallucinates APIs and config options when I ask it for help.

With more mainstream libraries it's pretty good though