Technology@lemmy.worldEnglish · 10 months ago

How backdoors could be placed in LLMs and how they could be detected

youtu.be

How backdoors could be placed in LLMs and how they could be detected

youtu.be

TerranFenrir@lemmy.ca to

Technology@lemmy.worldEnglish · 10 months ago

AI Sleeper Agents: How Anthropic Trains and Catches Them

youtu.be

In this video, we explain how Anthropic trained "sleeper agent" AIs to study deception. A "sleeper agent" is an AI model that behaves normally until it encou...

Chat

ferret@sh.itjust.works
link
fedilink
English
arrow-up
2·
10 months ago
finn is linuxmemes moderator

Technology@lemmy.world

technology@lemmy.world

Create a post

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: [email protected]

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related news or articles.
Be excellent to each other!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
Check for duplicates before posting, duplicates may be removed
Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

Visibility: Public

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

3.75K users / day
9.59K users / week
16.5K users / month
31.8K users / 6 months
1 local subscriber
85.8K subscribers
7.93K Posts
274K Comments
Modlog