Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Opus 4.7

anthropic.com

Post reply on HN
Print view View original

921–930 of 1001 posts

Re: Claude Opus 4.7

#921

Post by ljm »

beaker52 wrote: post #893
JamesSwift wrote: post #460

Earlier quoted context omitted.

Its especially concerning / frustrating because boris’s reply to my bug report on opus being dumber was “we think adaptive thinking isnt working” and then thats the last I heard of it: https://news.ycombinator.com/item?id=47668520 Now disabling adaptive thinking plus increasing effort seem to be what has gotten me back to baseline performance but “our internal evals look good“ is not good enough right now for what ma…

It doesn’t really come as a surprise to me that these companies are struggling to reliably fix issues with software which relies on a central component which is nondeterministic. But they made their own bed with that one.

I've noticed a lack of product cohesion in general and it does make me wonder if it's a result of dogfooding AI.

For example, chat, cowork and code have no overlap - projects created in one of the modes are not available in another and can't be shared.

As another example, using Claude with one of their hosted environments has a nice integration with GitHub on the desktop, but some of it also requires 'gh' to be installed and authenticated, and you don't have that available without configuring a workaround and sharing a PAT. It doesn't use the GH connector for everything. Switch to remote-control (ideal on Windows/WSL) or local and that deep integration is gone and you're back to prompting the model to commit and push and the UI isn't integrated the same.

Cowork will absolutely blow through your quota for one task but chat and code will give you much more breathing room.

Projects in Code are based on repos whereas in Chat and Cowork they are stateful entities. You can't attach a repo to a cowork project or attach external knowledge to a code project (and maybe you want that because creating a design doc or doing research isn't a programming task or whatever)

Use Claude Code on the CLI and you can't provide inline comments on a plan. There is a technical limitation there I suppose.

The desktop app is very nice and evolving but it's not a single coherent offering even within the same mode of operation. And I think that's something that is easy to do if you're getting AI to build shit in a silo.

Re: Claude Opus 4.7

#922

Post by misja111 »

sevenseacat wrote: post #920

Everything just takes so long now. 2-3 minutes to think after reading a few files before it wants to make a small change. I'm trying to lean in to LLMs like management wants, but a few times today I literally gave up and fixed the issues myself because I debugged them and fixed them while Claude was still thinking about them.

Well the fix is simple, just use 4.6 or even 4.5

Re: Claude Opus 4.7

#923

Post by misja111 »

pkilgore wrote: post #688
JamesSwift wrote: post #460

Earlier quoted context omitted.

Its especially concerning / frustrating because boris’s reply to my bug report on opus being dumber was “we think adaptive thinking isnt working” and then thats the last I heard of it: https://news.ycombinator.com/item?id=47668520 Now disabling adaptive thinking plus increasing effort seem to be what has gotten me back to baseline performance but “our internal evals look good“ is not good enough right now for what ma…

Seconded. After disabling adaptive thinking and using a default higher thinking, I finally got the quality I'm looking for out of Opus 4.6, and I'm pleased with what I see so far in Opus 4.7. Whatever their internal evals say about adaptive thinking, they're measuring the wrong thing.

Is 4.6 without adaptive thinking better than 4.5? Honest question. I switched back to 4.5 because 4.6 seemed mostly to take longer and consume more tokens, without noticeable improvement in the end result.

Re: Claude Opus 4.7

#924

Post by robeym »

robeym wrote: post #526

Working on some research projects to test Opus 4.7. The first thing I notice is that it never dives straight into research after the first prompt. It insists on asking follow-up questions. "I'd love to dive into researching this for you. Before I start..." The questions are usually silly, like, "What's your angle on this analysis?" It asks some form of this question as the first follow-up every time. The second obser…

I'm also noticing today that the model is hanging a lot. 5 min in, 50 tokens. Stuck in "Still here, still at it..."

Re: Claude Opus 4.7

#925

Post by holoduke »

misja111 wrote: post #922
sevenseacat wrote: post #920

Everything just takes so long now. 2-3 minutes to think after reading a few files before it wants to make a small change. I'm trying to lean in to LLMs like management wants, but a few times today I literally gave up and fixed the issues myself because I debugged them and fixed them while Claude was still thinking about them.

Well the fix is simple, just use 4.6 or even 4.5

Or write a local Gemma4 tool mcp for simple tool operations. Works seriously good. Basic tool use like command lining, greps, seds etc is milisec delay with about 100 tokens/sec on my m4.

Re: Claude Opus 4.7

#926

Post by keepamovin »

I like how HN has shifted from hating everything about AI, refusing to use it because HNers are 'too smart'/'too good', to now using it for everything and having strong opinions about it. It was inevitable, I suppose.

Re: Claude Opus 4.7

#929

Post by K0IN »

it costs the same as opus 4.6 as far as i can tell, and github copilot still charges more than double than for 4.6 (3x for 4.6 and 7.5x for 4.7), kinda uncool and a turnoff to test it (in copilot) out.

Re: Claude Opus 4.7

#930

Post by amelius »

keepamovin wrote: post #926

I like how HN has shifted from hating everything about AI, refusing to use it because HNers are 'too smart'/'too good', to now using it for everything and having strong opinions about it. It was inevitable, I suppose.

It's probably not fun to go from self-proclaimed intellectual to advanced calculator.
Post reply on HN