The Pentagon situation is the real test. Most ethics policies hold until there's actual money on the table. PBC structure helps at the margins but boards still feel fiduciary pressure. Hoping Anthropic handles it differently but the track record for this kind of thing is not encouraging.
Have you tried framing the hypothesis as a question in the dispatch prompt rather than a statement? Something like -- possible cause: X, please verify before proceeding -- instead of stating it as fact. Might break the assumption inheritance without changing the overall structure.
After a month of obliterating work with 4.5, I spent about 5 days absolutely shocked at how dumb 4.6 felt, like not just a bit worse but 50% at best. Idk if it's the specific problems I work on but GP captured it well - 4.5 listened and explored better, 4.6 seems to assume (the wrong thing) constantly, I would be correcting it 3-4 times in a row sometimes. Rage quit a few times in the first day of using it, thank god I found out how to dial it back.
Genuinely one of the more interesting model evals I've seen described. The sunk cost framing makes sense -- 4.5 doubles down, 4.6 cuts losses faster. 9 days vs 59 is a wild result. Makes me wonder how much of the regression complaints are from people hitting 4.6 on tasks where the first approach was obviously correct.
Notably 45 out of the 50 days of improvement were in two specific dungeons (Silph Co and Cinnabar Mansion) where 4.5 was entirely inadequate and was looping the same mistaken ideas with only minor variation, until eventually it stumbled by chance into the solution. Until we saw how much better it did in those spots, we weren't completely sure that 4.6 was an improvement at all!
