Ask an agent a question the internet has an opinion about, and it doesn't look for the answer – it builds a case for the one its training data already handed it, using real tools to manufacture real-looking evidence. Here's how to make it prosecute the other side.
When Anthropic's status page showed elevated errors on June 16, the visible failures were the easy part. The dangerous part was the requests that succeeded.
Having one model produce the work and another inspect the result is not review. Review means seeing the work happen, not just judging what survived.
Engineering assumes a target that holds still. Frontier language models do not. The fastest way to identify someone who has not run an AI system in production is to watch them say 'prompt engineering' anyway.
Different agents in a workflow don't create independence when they share the weights. The architecture is real engineering. It's just not the check your slide says it is.
Zwischen