#refusals

Frances Lee on American elections - Marginal REVOLUTION

Marginal REVOLUTION·Tyler Cowen·about 22 hours ago

#marginalrevolution #election #concede #candidates #political

More likely than interference with the election is that unsuccessful office-seekers will refuse to concede, claiming their opponents cheated. Nothing is more basic to democratic legitimacy than the loser’s consent.…

15s

NEW: malware developers added nuclear & biological weapons text to to their spyware.

Goal? To trigger LLM safety refusals... so that their spyware wouldn't be analyzed by an AI security scanner.

Cleanest practical example I can think of for why over-indexing on first order https://t.co/WLxe0LWo8s

🖼️

449Read More

NEW: malware developers added nuclear & biological weapons text to to their spyware. Goal? To trigger LLM safety refusals... so that their spyware wouldn't be analyzed by an AI security scanner. Cleanest practical example I can think of for why over-indexing on first order https://t.co/WLxe0LWo8s

Hacker News·5 months ago

#U4ElWg4W

#twitter #malware #spyware #safety #refusals

NEW: malware developers added nuclear & biological weapons text to to their spyware. Goal? To trigger LLM safety refusals... so that their spyware wouldn't be analyzed by an AI security scanner.…

15s

Menu

Frances Lee on American elections - Marginal REVOLUTION

NEW: malware developers added nuclear & biological weapons text to to their spyware. Goal? To trigger LLM safety refusals... so that their spyware wouldn't be analyzed by an AI security scanner. Cleanest practical example I can think of for why over-indexing on first order https://t.co/WLxe0LWo8s