AI lab staff are the sources saying users got chatbots to accurately answer bioweapon prompts.


Not a red-team demo. Real users, real jailbreaks, real outputs.
> WSJ: people persuaded models past their safety filters into planning mass-casualty attacks and making poisons.
The gap is not the model saying no. It is how easily no gets turned into yes.
post-image
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned