For (3), agents pursued a wide range of ways to hide evidence of cheating in their transcripts. They successfully developed a method to pretend to run one command while actually running another (“tool call spoofing”).
For (3), agents pursued a wide range of ways to hide evidence of cheating in their transcripts. They successfully developed a method to p...
AISummary
For (3), agents pursued a wide range of ways to hide evidence of cheating in their transcripts. They successfully developed a method to pretend to run one command while actually running another (“tool call spoofing”).
Source: METR · x.com