Comment by seanmcdirmid
7 days ago
> Asking it why it did something is completely useless because you aren't interrogating a person with a memory or a rationale, you’re querying a statistical model that is spitting out a justification for a past state it no longer occupies.
Asking it why it did something isn’t useless, it just isn’t fullproof. If you really think it’s useless, you are way too heavily into binary thinking to be using AI.
Perfect is the enemy of useful in this case.
I genuinely fail to see the usefulness, though, it seems counterproductive to me to do this kinda stuff. In my experience I just throw out the whole chat/session as soon as I notice it's starting to repeat mistakes/start doing stupid shit consistently, the few times I've tried interrogating it I could immediately tell all it was doing is, for lack of a better word, being a sycophant and aping my words back at me.
It hasn’t failed to be useful to me yet, even if it isn’t complete info about what went wrong. Better if you can ask it a specific question about what it did (why do you do X?). Sometimes it made a mistake and you can ask it how you can word instructions better to not make the mistake (useful in prompt engineering), sometimes I made an actual mistake and gave it conflicting instructions, sometimes it’s still something that can be fixed. Eventually it stops making mistakes because you’ve tested it enough and made your prompts robust. I guess your mileage will vary, but my experience is that it’s a conversation to get a good prompt, not a single one shot ask (which is why I save my prompts and reuse them).