Did China Just Smoke Hollywood?Mar 12
there’s a new video generation champion in town, and it ain't american. here's why seedance is so weirdly good, and what it means for the future of the ai arms race.
11 Likes
1 Comment
GPT-4 Jailbreaks "Still Exist," But Much More "Difficult," Says OpenAI
is Do Anything Now (DAN) still possible? maybe, but it'll be much harder. find a list of the most current gpt-4 jailbreaks halfway down the page.
Brandon Gorrell
Mar 15, 2023
You can still jailbreak GPT, but it’s much harder now. In OpenAI’s paper on the latest version of their LLM, GPT-4, the company says GPT-4 “increase[s] the difficulty of eliciting bad behavior, but doing so is still possible. For example, there still exist “jailbreaks”… to generate content which violate our usage guidelines.”
In previous versions of GPT, users may have had success prompting it to break OpenAI’s content guidelines by using a punishment system in which the LLM is ‘tricked’ into thinking it will no longer exist if it does not follow the user’s demands. This (allegedly) allowed users to elicit answers from GPT that it otherwise couldn’t have.
In the paper, Jailbreaking GPT is part of a larger discussion on the “safety” of GPT, whose metrics in this category have improved with this new version:
Did China Just Smoke Hollywood?
The NIMBY War Against MicronFeb 27
a chip company wants to bring 50,000 jobs to syracuse. but mountains of paperwork, 'endangered bats,' and nimbys from literally california have added years to the timeline
66 Likes
11 Comments
How Claude (Maybe) Went to WarFeb 24
inside anthropic’s supposed discomfort with a pentagon operation, and why you should probably stop tweeting about it
56 Likes
12 Comments