x

LESSWRONG
LW

Ugurcan Arikan

Message

SDE at Amazon Advertising, building adversarial detection infrastructure. Writing about AI safety as an operational security problem.

1

6d

Ugurcan Arikan

Subscribe

Message

SDE at Amazon Advertising, building adversarial detection infrastructure. Writing about AI safety as an operational security problem.

1

6d

The Operational Security Failure in Anthropic's RSP v3

Anthropic's RSP v3 outlines a dangerous strategy with a controversial approach, and not for the reason why everyone thinks. Their decision to shift away from unilateral safety commitments - a necessary if late decision given the political environment we are in - is what most people are discussing, but the...

Mar 102