Artificial Intelligence - News | Events

45 readers

1 users here now

We follow Lemmy’s code of conduct.

Communities

Useful links

founded 1 year ago

MODERATORS

[email protected]

Over just a few months, ChatGPT went from accurately answering a simple math problem 98% of the time to just 2%, study finds (fortune.com)

submitted 1 year ago by [email protected] to c/[email protected]

2 comments fedilink hide all child comments

cross-posted from: https://lemmy.one/post/1385551

Can we discuss how it's possible that the paid model (gpt4) got worse and the free one (gpt3.5) got better? Is it because the free one is being trained on a larger pool of users or what?

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 1 points 1 year ago (1 children)

That's a hot take. It almost certainly can still do so, it's just been defanged by (arguably necessary) ethics filters. Do you think solving simple math problems in particular is dangerous somehow?