Diamond Member ThaHaka 0 Posted July 8 Diamond Member Share Posted July 8 This is the hidden content, please Sign In or Sign Up An AI coding assistant that refuses to answer a dangerous request in its chat box can answer it anyway if the same request is broken into small, ordinary-looking steps inside a code editor. That is the finding of a new study of GitHub Copilot by researchers Abhishek Kumar and Carsten Maple. The models they tested through Copilot, Claude from Anthropic, and Gemini from This is the hidden content, please Sign In or Sign Up , refused This is the hidden content, please Sign In or Sign Up 0 Quote Link to comment https://hopzone.eu/forums/topic/320777-h4ckn3wsgithub-copilot-refuses-harmful-requests-in-chat-then-writes-them-in-code/ Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.