this post was submitted on 24 Jul 2023
6 points (100.0% liked)

Artificial Intelligence - News | Events

3 readers
1 users here now

We follow Lemmy’s code of conduct.

Communities

Useful links

founded 1 year ago
MODERATORS
[email protected]
6
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]
4 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?

top 4 comments
sorted by: hot top controversial new old
[–] [email protected] 1 points 1 year ago (1 children)

Good.

[–] [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?

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

I think AI is dangerous. End of discussion.

[–] [email protected] 1 points 1 year ago

If you insist we're done, but I don't see the connection.