Hacker News new | past | comments | ask | show | jobs | submit
> because 'I don't know' is not in the vocabulary of any AI.

That is clearly false. I’m only familiar with Opus, but it quite regularly tells me that, and/or decides it needs to do research before answering.

If I instruct it to answer regardless, it generally turns out that it indeed didn’t know.

I haven't had that at all, not even a single time. What I have had is endless round trips with me saying 'no, that can't work' and the bot then turning around and explaining to me why it is obvious that it can't work... that's quite annoying.
Try something like:

> Please carefully review (whatever it is) and list out the parts that have the most risk and uncertainty. Also, for each major claim or assumption can you list a few questions that come to mind? Rank those questions and ambiguities as: minor, moderate, or critical.

> Afterwards, review the (plan / design / document / implementation) again thoroughly under this new light and present your analysis as well as your confidence about each aspect.

There's a million variations on patterns like this. It can work surprisingly well.

You can also inject 1-2 key insights to guide the process. E.g. "I don't think X is completely correct because of A and B. We need to look into that and also see how it affects the rest of (whatever you are working on)."

loading story #47391070