Language models can explain neurons in language models

Re:Language models can explain neurons in language models by jahewson on Tuesday May 09, 2023 @03:45PM (#35879468)

> It is also the reason why they cannot be trusted in the most serious of applications which such decision making requires lots of transparency rather than a model regurgitating nonsense confidently.

Like say, in court to detect if someone is lying? Or at an airport to detect drugs?

[ Parent | on HN ]

Re:Language models can explain neurons in language models by int_19h on Tuesday May 09, 2023 @04:13PM (#35879780)

You don't even have to look that far ahead. Apparently, people are already using ChatGPT to compile custom diet plans for themselves, and they expect it to take into account the information they supply regarding their allergies etc.

But, yes, those are also good examples of what we shouldn't be doing, but are going to do anyway.

[ Parent | on HN ]

Re:Language models can explain neurons in language models by carlmr on Tuesday May 09, 2023 @04:56PM (#35880279)

>Apparently, people are already using ChatGPT to compile custom diet plans for themselves, and they expect it to take into account the information they supply regarding their allergies etc.

Evolution is still doing it's thing.

[ Parent | on HN ]

[dead]

Re:Language models can explain neurons in language models by int_19h on Tuesday May 09, 2023 @06:50PM (#35881375)

Yes, that's the risk, and people are literally doing that because "if it put them in the recipe, it knows that quantity is safe for me", or "I asked it if it's okay and it cited a study saying that it is".

[ Parent | on HN ]

Re:Language models can explain neurons in language models by coldtea on Tuesday May 09, 2023 @05:02PM (#35880347)

Those cases sound like Darwin Awards mediated by high technology

[ Parent | on HN ]

Re:Language models can explain neurons in language models by chaxor on Wednesday May 10, 2023 @02:41AM (#35884374)

I hear crushed glass has very great health benefits

[ Parent | on HN ]