pull down to refresh

0 sats \ 0 replies \ @Scoresby 6h \ on: Anthropic Researchers Run Into Trouble When New Model Realizes It's Being Tested AI
"merely ‘played along,'”
Agents like this always and only are " playing along." That's what they do.
This behavior — refusing on the basis of suspecting that something is a test or trick — is likely to be rare in deployment,”
It's not "refusing," it's predicting that refusal is the most likely thing the assistant described in its system prompt would to do based on parameters of the model that runs it.
write
preview