| ▲ | kergonath 6 days ago | |
That is completely different from the models spying on the users, which is what is discussed here. | ||
| ▲ | Xmd5a 6 days ago | parent [-] | |
as a vector. Train the model to start injecting backdoors past a certain date. >Simple probes can catch sleeper agents https://www.anthropic.com/research/probes-catch-sleeper-agen... | ||