Hacker News new | ask | show | jobs
by babycheetahbite 287 days ago
Does anyone have any suggestions for approaches they are taking to avoid the potential for this? Something I did recently in ChatGPT's 'Instructions' box (so far I have only used ChatGPT) is requesting it to "Make me think through the problem before just giving me the answer." and a few other similar notes.
3 comments

Nothing, because it’s a poorly designed study that has no peer review and has been absolutely derided in the scientific community for the conflicts of interest the author has and how sensationally she spun it without peer review
At the very least, don’t use LLMs tightly integrated into your IDE. Keep them at arms length, use them the way you use a search engine.
yes, in a software engineering context, always use ask mode instead of agent mode unless youre truly doing dumb, tedious work that youve done many times before