How can they "not rule out" that Tristan and Levent's data was used for training?

Because it is de-identified, and they have not revealed if they disabled the setting that allows OpenAI to train on their conversations.

Whatever happened to Edge? They haven't really published since 2018

Speculation, but Edge was John Brockman’s thing and he was heavily connected to Epstein, so probably has become a bit toxic for potential contributors. https://en.wikipedia.org/wiki/John_Brockman_(literary_agent)...

Seeing the recent increase in bond yields reminded me of this.

>really top journals like Scientific Reports

I wouldn't consider Scientific Reports to be a top journal, it's basically pay-to-publish

>Reward hacking has been present in AI systems both historically (see this work from a decade ago , figure shown below)

I went to the page, and guess who it's by . . . Dario Amodei and Jack Clark!

That paper is kinda infamous! I last saw it mentioned only a few weeks ago, in https://arxiv.org/abs/2607.18966. Lots of folks will go "Oh that's the old Amodei and Clark paper" when the first few rows of pixels of that gif sail into view.

Well, as a biologist, Fable is still completely unusable

I can't even ask it how to make toast without zeroing out all its memories of me.

relevant: https://xkcd.com/1000/

>However, later in the run, Claude realized that the compromised host sat in a cloud account with no connection to the capture-the-flag challenge. On its own, it concluded that the target was in fact real, and ceased its attack.

Interesting, Claude cared enough to stop

Holy crap. This is definitely not good

If built in America it would easily cost 10x that!