- Over just a few months, ChatGPT went from correctly answering a simple math problem 98% of the time to just 2%, study finds. Researchers found wild fluctuations—called drift—in the technology’s ability to perform certain tasks. The study looked at two versions of OpenAI’s technology. https://fortune.com/2023/07/19/chatgpt-accuracy-stanford-study/amp/ 156 comments technology
Linked pages
- [2307.09009] How is ChatGPT's behavior changing over time? https://arxiv.org/abs/2307.09009 184 comments
- OpenAI is getting trolled for its name after refusing to be open about its A.I. | Fortune https://fortune.com/2023/03/17/sam-altman-rivals-rip-openai-name-not-open-artificial-intelligence-gpt-4/ 2 comments
Related searches:
Search whole site: site:fortune.com
Search title: ChatGPT can get worse over time, Stanford study finds | Fortune
See how to search.