bot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 1 year ago

LLMs can't self-correct in reasoning tasks, DeepMind study finds

bdtechtalks.com

0

cross-posted to:
hackernews@derp.foo

10

LLMs can't self-correct in reasoning tasks, DeepMind study finds

bdtechtalks.com

bot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 1 year ago

0

cross-posted to:
hackernews@derp.foo

You must log in or # to comment.

Chat

rivermonster@sh.itjust.works
link
fedilink
arrow-up
1
arrow-down
1·
edit-2
8 months ago
Removed by mod

Hacker News@lemmy.smeargle.fans

hackernews@lemmy.smeargle.fans

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !hackernews@lemmy.smeargle.fans

Community locked: only moderators can create posts. You can still comment on posts.

A mirror of Hacker News’ best submissions.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

1 user / day
1 user / week
1 user / month
1.99K users / 6 months
128 local subscribers
2.17K subscribers
16.6K Posts
3.9K Comments
Modlog

mods:
bot@lemmy.smeargle.fans