How 'Bad Likert Judge' Breaks AI Safety Rules
Jan 9 2025
Length: 3 mins
Podcast

Failed to add items

Sorry, we are unable to add the item because your shopping cart is already at capacity.

Add to basket failed.

Please try again later

Add to wishlist failed.

Please try again later

Remove from wishlist failed.

Please try again later

Adding to library failed

Please try again

Follow podcast failed

Unfollow podcast failed

How 'Bad Likert Judge' Breaks AI Safety Rules

Listen for free

View show details

Summary
The 'Bad Likert Judge' jailbreak technique exploits AI models by using psychometric scales to bypass safety filters, increasing attack success rates by over 60% and raising critical concerns about LLM vulnerabilities.
Check out the transcript here: Easy English AI News

Show More Show Less

Only £0.99 a month for the first 3 months. Pay £0.99 for the first 3 months, and £7.99/month thereafter. Renews automatically. Terms apply. Start my membership

Show More Show Less

What listeners say about How 'Bad Likert Judge' Breaks AI Safety Rules

Average customer ratings

Reviews - Please select the tabs below to change the source of reviews.

Audible.co.uk reviews

Amazon reviews

No Reviews are Available

Report a review on Amazon