WF-02JQN6
Purdue study finds ChatGPT wrong over half the time on software questions
A study by Purdue University found that ChatGPT provided incorrect answers to over half of 517 software development questions from Stack Overflow. Despite the errors, 34% of users preferred ChatGPT's answers over human responses. The study warns that relying on ChatGPT for coding could jeopardize programmers' professional reputations.
- Organisation involved
- OpenAI
- Product, system or model
- ChatGPT
Where this came from
Attribution
This incident was imported from techmonitor.ai. Our additions to it — the structured fields, the translation, the checks against other reports — are published under the same licence.
This is a record of what was reported, not a finding that anyone broke the law. If it names your organisation and you believe it is wrong, the corrections process is free and open to everyone.