muelltonne@feddit.org to

Technology@lemmy.worldEnglish · 1 month ago

It Only Takes A Handful Of Samples To Poison Any Size LLM, Anthropic Finds

14

It Only Takes A Handful Of Samples To Poison Any Size LLM, Anthropic Finds

muelltonne@feddit.org to

Technology@lemmy.worldEnglish · 1 month ago

It stands to reason that if you have access to an LLM’s training data, you can influence what’s coming out the other end of the inscrutable AI’s network. The obvious guess is that…

Chat

phutatorius@lemmy.zip
link
fedilink
English
arrow-up
1·
29 days ago
DO IT. Break that shit.
- SaveTheTuaHawk@lemmy.ca
  link
  fedilink
  English
  arrow-up
  1·
  29 days ago
  It’s happening. I’ve been resampling queries every few months and the deviation of wrong to true responses is getting bigger.

Technology@lemmy.world

technology@lemmy.world

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.

3.35K users / day
9.13K users / week
14.8K users / month
14.9K users / 6 months
1 local subscriber
78.7K subscribers
872 Posts
19.9K Comments
Modlog