Sunday, July 7, 2024

A study of GPT-3.5-based ChatGPT's ability to solve 728 coding problems: fairly good at solving problems that existed before 2021, but struggles with newer ones (Michelle Hampson/IEEE Spectrum)

Michelle Hampson / IEEE Spectrum:
A study of GPT-3.5-based ChatGPT's ability to solve 728 coding problems: fairly good at solving problems that existed before 2021, but struggles with newer ones  —  This article is part of our exclusive IEEE Journal Watch series in partnership with IEEE Xplore.



at
Labels:

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

How DeepSeek outpaced OpenAI at 3% of the cost: open-source approach, pure reinforcement learning, not supervised fine-tuning, and building on DeepSeek-R1-Zero (Matt Marshall/VentureBeat)

Matt Marshall / VentureBeat : How DeepSeek outpaced OpenAI at 3% of the cost: open-source approach, pure reinforcement learning, not supe...