i think it is quite clear that staying with opus 4.6 is the way to go, on top of the inflation, 4.7 is quite... dumb. i think they have lobotomized this model while they were prioritizing cybersecurity and blocking people from performing potentially harmful security related tasks.

▲

bcherny 4 hours ago | parent | next [-]

Hey, Boris from the Claude Code team here. People were getting extra cyber warnings when using old versions of Claude Code with Opus 4.7. To fix it, just run claude update to make sure you're on the latest.

Under the hood, what was happening is that older models needed reminders, while 4.7 no longer needs it. When we showed these reminders to 4.7 it tended to over-fixate on them. The fix was to stop adding cyber reminders.

More here: https://x.com/ClaudeDevs/status/2045238786339299431

▲

matheusmoreira 8 minutes ago | parent | next [-]

What is your response to:

> 4.7 is quite... dumb. i think they have lobotomized this model

Is adaptive thinking still broken? Why was the option to disable it taken away?

▲

bakugo 4 hours ago | parent | prev [-]

How do you justify the API and web UI versions of 4.7 refusing to solve NYT Connections puzzles due to "safety"?

https://x.com/LechMazur/status/2044945702682309086

▲

templar_snow 4 hours ago | parent [-]

To be fair, reading the New York Times is a safety risk for any intelligent life form these days. But still.

	▲	maleldil 4 hours ago \| parent [-]
		You don't need to subscribe to the NYT to play the games. There's a separate subscription.

▲

vessenes 4 hours ago | parent | prev [-]

4.7 is super variable in my one day experience - it occasionally just nails a task. Then I'm back to arguing with it like it's 2023.

	▲	aenis 4 hours ago \| parent \| next [-]
		My experience as well, unfortunately. I am really looking forward to reading, in a few years, a proper history of the wild west years of AI scaling. What is happening in those companies at the moment must be truly fascinating. How is it possible, for instance, that I never, ever, had an instance of not being able to use Claude despite the runaway success it had, and - i'd guess - expotential increase in infra needs. When I run production workloads on vertex or bedrock i am routinely confronted with quotas, here - it always works.
	▲	dgellow 4 hours ago \| parent \| prev [-]
		That has been my Friday experience as well… very frustrating to go back to the arguing, I forgot how tense that makes me feel