It’s interesting that it can “recognize” the actions as clearly illogical afterwards, as if made by someone panicking, but will still make them in the first place
Yeah I don’t use LLMs often, but use ChatGPT occasionally, and sometimes when asking technical/scientific questions it will have glaring contradictions that are just completely wrong for no reason. One time when this happened I told it that it fucked up and to check it’s work, and it corrected itself immediately. I tried again to see if I could get it to overcorrect or something, but it didn’t go for it.
So as weird as it sounds, I think adding “also make sure to always check your replies for logical consistency” to its base prompt would improve things.
Yeah I don’t use LLMs often, but use ChatGPT occasionally, and sometimes when asking technical/scientific questions it will have glaring contradictions that are just completely wrong for no reason. One time when this happened I told it that it fucked up and to check it’s work, and it corrected itself immediately. I tried again to see if I could get it to overcorrect or something, but it didn’t go for it.
So as weird as it sounds, I think adding “also make sure to always check your replies for logical consistency” to its base prompt would improve things.
and just like that we’re back to computers doing precisely what we tell them to do, nothing more and nothing less.
one day there’s gonna be a sapient LLM and it’ll just be a prompt of such length that it qualifies as a full genome
This unironically works, it’s basically the same reason why chain-of-reasoning models produce better outputs