Mastodon discussion Discussions Jul 29 2 views

It's Frighteningly Easy to Jailbreak Some Frontier AI Modelshttps://www.wired.com/story/jailbreaking-ai-models-google-an...

by WIRED

It's Frighteningly Easy to Jailbreak Some Frontier AI Modelshttps://www.wired.com/story/jailbreaking-ai-models-google-anthropic-openai-spacexai/#AI #Security #Tech

Read Original

Metadata

Reblogs Count: 2
Account: wired@robot.villas

Mastodon discussion 6m ago

David Sacks on X: Some thoughts on Dario's postArticle URL: https://twitter.com/DavidSacks/status/2089227290769080656 Co...

David Sacks on X: Some thoughts on Dario's postArticle URL: https://twitter.com/DavidSacks/status/2089227290769080656 Comments URL: https://news.ycombinator.com/item?id=49329844 Po...

Mastodon discussion 8m ago

@davecbBeen considering going in that direction rather than an all-out ban. Currently, my feeling is it’s acceptable to ...

@davecbBeen considering going in that direction rather than an all-out ban. Currently, my feeling is it’s acceptable to use if its clear up-front that:An 80% correct answer is acce...

Mastodon discussion 8m ago

It's Frighteningly Easy to Jailbreak Some Frontier AI Modelshttps://www.wired.com/story/jailbreaking-ai-models-google-an...

Metadata

Related

David Sacks on X: Some thoughts on Dario's postArticle URL: https://twitter.com/DavidSacks/status/2089227290769080656 Co...

@davecbBeen considering going in that direction rather than an all-out ban. Currently, my feeling is it’s acceptable to ...

@jzb Please #boycott all #AI #TechBros and wealthy abusers.