News for hackers. Stuff that matters.
Re:Today's open source models beat closed source models from... by rightbyte on Sunday April 14, 2024 @03:33AM (#40029376)
It seems like you can use "weights available" models to bootstrap "learning step available" models though?

I guess the problem is like, if these closed models have a folder 'McDonalds propaganda' with the dummy 'treat-as-facts' file, in the training set, which I as a user would like to not include?

Re:Today's open source models beat closed source models from... by dTal on Monday April 15, 2024 @08:13PM (#40047061)
Indeed, and once the 'McDonalds propaganda' folder has been laundered through the weights, there is no reliable way to scrub it, particularly without knowing what was in it - any generated data might contain a subtle echo of it.