James Lucassen
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Probe monitors seem to perform realistically in simulated control environments
Aswin Surya and James Lucassen, working at Redwood Research, test whether probes that read a model's internal activations catch attacks as well in simulated computer environments as in real ones. In one agent and one task suite, the catch rate differed little, though a probe could tell simulated from real.