Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
OpenAI adds new safety net to prevent ChatGPT from advising on creating viruses (hindustantimes.com)
5 points by Utubepublisher 5 months ago | hide | past | favorite | 1 comment


I do red teaming for a competition in an educational environment. A lot of it involves writing custom malware for the environment. All these "safety nets" suck, because they stop the models from helping me with my work for no good reason. Thankfully, people have been making open models which are much more useful than the ones served by ClosedAI.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: