logoalt Hacker News

daishi55last Tuesday at 10:40 PM1 replyview on HN

In this case they didn’t know what they were looking for. They just wanted some new, non-trivial exploit.

For the vast majority of corporate usage of AI for SWE, you have a much better idea of what you want, or what the problem is, etc etc. And communicating that to the model effectively is absolutely a skill. I see colleagues every day who very much do not have that skill.


Replies

niccllast Tuesday at 10:50 PM

I agree with this in general but I think there's a nuance. 'dumb' prompts can get the result, but require more back-and-forth with the model and more token usage when compared to a crafted prompt

show 1 reply