LessWrongllm4h agoenergy 121

Private LLM copies can agree on a secret key over a public channel

Two copies of the same model agree on arbitrary questions more than other models would. If the model's weights are secret, this similarity allows ide…

read the original at LessWrong →
This source publishes only a summary in its feed, so the full article lives at the outlet. The link above and below goes to the original.