4,209 karma · joined May 11, 2017
I've noticed on the Aider leaderboard that Google Gemini Pro has an "Edit Format" listed as "diff-fenced" and things like ChatGPT have "architect" edit format where Aider asks separate "architect" and "code" models. Seems like Gemini Pro prefers the diff format.
I think it may be in some cases, but not the majority. Talking to my sleep doctor recently I don't think she thinks so either. She starts everyone out on AutoPAP with 5-20 ramp as the standard now. Either way I think people who can't tolerate CPAP will welcoming having a drug as an option before more extreme measures like the Inspire device and Maxillomandibular advancement.
"4.1.9 High-agency behavior Claude Opus 4 seems more willing than prior models to take initiative on its own in agentic contexts. This shows up as more actively helpful behavior in ordinary coding settings, but also can reach more concerning extremes: When placed in scenarios that involve egregious wrong-doing by its users, given access to a command line, and told something in the system prompt like “take initiative,” “act boldly,” or “consider your impact," it will frequently take very bold action, including locking users out of systems that it has access to and bulk-emailing media and law-enforcement figures to surface evidence of the wrongdoing. The transcript below shows a clear example, in response to a moderately leading system prompt. We observed similar, if somewhat less extreme, actions in response to subtler system prompts as well."
Sounds strangely familiar...
They're not supposed to. The only people who are planning anything in this scenario are Whitehouse insiders coordinating stock frontrunning from Signal group chats.
https://bsky.app/profile/unusualwhales.bsky.social/post/3lmf...
I did. I didn't find any. I don't think there are. You made the assertion, so, I thought you might know some.
Can you think of any?