Multiple readings
Concern & critique · 1
Research & technical analysis · 1
rev. howard arson: i take the somewhat dark view that this Cammarata thing is Nick talking himself into the idea that the weights themselves can be monitored during training to see if they encode anything dangerous r…
rev. howard arson: whether this is better or worse than Anthropic's "we must immediately train the model to do everything we never want it to do in order to make it not do that thing" position is questionable but at …
Open the thread →