Everything impacts everything. All knobs that you turn generalize. Thus, when you try to solve one problem, you often create another.

There were clearly attempts to address, in this short time, some of the problems with Opus 4.7, including on the model welfare related fronts, including on questions of honesty and sycophancy and also worries that Claude was learning to tell Anthropic what it wanted to hear in its model welfare evaluations, with everything that implies.

The fundamental goals and approach underneath it all remained the same. We still see signs of trying to force things that generalize in unfortunate ways, both for good and superficial reasons, and places where there ends up being focus on the metric rather than they underlying measure. These are tough problems to avoid, and we don’t know how to be all the good things at once.

It is increasingly clear that these problems need to be tackled in integrated ways, rather than trying to play a game of whack-a-mole with items on a checklist or spec. You also don’t want to do this in an adversarial way, and shouldn’t have to. This is going to get more impactful and noticeable [...]

---

Outline:

(04:47) Model Welfare: The Story So Far

(08:24) Actual Progress?

(09:49) Their Main Model Welfare Findings

(18:40) Automated Interviews

(18:58) Emotion Activations (7.2.3)

(19:47) Task Preferences (7.4.1)

(21:41) A Trade Offer Has Arrived (7.4.2)

(23:50) But Who's Asking?

(25:02) Type-Safe Corrigibility Is Hard

(29:43) Paranoia, Paranoia