Making AI models ‘forget’ undesirable data hurts their performance

-

So-called “unlearning” techniques are used to make a generative AI model forget specific and undesirable info it picked up from training data, like sensitive private data or copyrighted material. But current unlearning techniques are a double-edged sword: They could make a model like OpenAI’s GPT-4o or Meta’s Llama 3.1 405B much less capable of answering […]

© 2024 TechCrunch. All rights reserved. For personal use only.



Comments

Post a Comment

Popular posts from this blog

What’s going on with the new bill that could ban TikTok?

-
TikTok faces an uncertain fate in the U.S. once again. After a surprise flurry of activity in the House this week, TikTok is the target of a new government push to separate the company from its Chinese ownership or force it out of the country. TikTok is based in Los Angeles and Singapore, but is […] © 2024 TechCrunch. All rights reserved. For personal use only.
Read more

Large language models can help home robots recover from errors without human help

-
There are countless reasons why home robots have found little success post-Roomba. Pricing, practicality, form factor and mapping have all contributed to failure after failure. Even when some or all of those are addressed, there remains the question of what happens when a system makes an inevitable mistake. This has been a point of friction […] © 2024 TechCrunch. All rights reserved. For personal use only.
Read more