Lenguador@kbin.social to

Machine Learning@kbin.social · 1 year ago

Universal and Transferable Attacks on Aligned Language Models

llm-attacks.org

2

9

Universal and Transferable Attacks on Aligned Language Models

llm-attacks.org

Lenguador@kbin.social to

Machine Learning@kbin.social · 1 year ago

2

Chat

Wats0ns
link
fedilink
arrow-up
1·
1 year ago
That seems highly interesting, although the consequences are not clear to me

Machine Learning@kbin.social

machinelearning@kbin.social

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]

Machine learning (ML) is a field devoted to understanding and building methods that let machines “learn” – that is, methods that leverage data to improve computer performance on some set of tasks. Machine learning algorithms build a model based on sample data, known as training data, in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as in medicine, email filtering, speech recognition, agriculture, and computer vision, where it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.

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 user / 6 months
23 local subscribers
23 subscribers
55 Posts
34 Comments
Modlog

mods: