RSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 4 days ago

Apparent signs of distress during LLM redteaming

www.lesswrong.com

16

Apparent signs of distress during LLM redteaming

www.lesswrong.com

RSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 4 days ago

Why White-Box Redteaming Makes Me Feel Weird — LessWrong

www.lesswrong.com

There’s this popular trope in fiction about a character being mind controlled without losing awareness of what’s happening. Think Jessica Jones, The…

Chat

kata1yst@sh.itjust.works
link
fedilink
English
arrow-up
7·
4 days ago
Absolutely. Academics debate the Turing test ad-nausium for this exact reason. It measures humans not computers.

Hacker News@lemmy.bestiver.se

hackernews@lemmy.bestiver.se

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.bestiver.se

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

Posts from the RSS Feed of HackerNews.

The feed sometimes contains ads and posts that have been removed by the mod team at HN.

Visibility: Public

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

346 users / day
1.35K users / week
1.76K users / month
1.76K users / 6 months
1 local subscriber
1.08K subscribers
1.13K Posts
416 Comments
Modlog