Mittwoch, 10. Juli 2024

The Ability of ChatGPT to Tackle Hard Problems:

via Robin Hanson: 

"its ability to generate functional code for 'hard' problems dropped from 40% to 0.66% after this time as well. 'A reasonable hypothesis for why ChatGPT can do better with algorithm problems before 2021 is that these problems are frequently seen in the training dataset'"

Keine Kommentare:

Kommentar veröffentlichen