![@Vega@feddit.it avatar](https://incremental.social/media/cache/resolve/avatar_thumb/0f/0a/0f0ae9a2cfd09fb7a195e7243787ff5dea0a242d45944f79d9ae5ef2d890f39b.jpg)
![@Vega@feddit.it cover](https://incremental.social/media/cache/resolve/user_cover/dc/91/dc913f0d4a128d078089daf412e9e131420b87e4e030c9430fd8ff8e22e21e06.jpg)
![@Vega@feddit.it avatar](https://incremental.social/media/cache/resolve/avatar_thumb/0f/0a/0f0ae9a2cfd09fb7a195e7243787ff5dea0a242d45944f79d9ae5ef2d890f39b.jpg)
Roman Dmitrievič Protasevič è stato arrestato dalla dittatura bielorussa dopo che il suo volo civile Europeo è stato dirottato e costretto ad atterrare da caccia militari bielorussi. Per non dimenticare il suo nome e quanto accaduto.
This profile is from a federated server and may be incomplete. Browse more on the original instance.
[Thread, post or comment was deleted by the author]
rule (lemmy.ml)
google engineer (lemmy.world)
Poisoned AI went rogue during training and couldn't be taught to behave again in 'legitimately scary' study (www.livescience.com)
Poisoned AI went rogue during training and couldn't be taught to behave again in 'legitimately scary' study::AI researchers found that widely used safety training techniques failed to remove malicious behavior from large language models — and one technique even backfired, teaching the AI to recognize its triggers and better...