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

Claude Opus 4.1

anthropic.com

Post reply on HN
Print view View original

221–230 of 344 posts

Re: Claude Opus 4.1

#221

Post by sky2224 »

jzig wrote: post #10

I'm confused by how Opus is presented to be superior in nearly every way for coding purposes yet the general consensus and my own experience seem to be that Sonnet is much much better. Has anyone switched to entirely using Opus from Sonnet? Or maybe switching to Opus for certain things while using Sonnet for others?

I've found with limited context provided in your prompt, opus is just awful compared to even gpt-4.1, but once I give it even just a little bit more of an explanation, it jumps leagues ahead.

Re: Claude Opus 4.1

#222

Post by Filligree »

kelnos wrote: post #203
wahnfrieden wrote: post #152

Earlier quoted context omitted.

Correct. Claude Code Max with Opus. Don’t even bother with Sonnet.

I wouldn't be too prescriptive. I have Pro, and it's fine. I'm not an incredibly heavy user (yet?); I've hit the rate limits a couple times, but not to the point where I'm motivated to spend more. I haven't tried it myself, but I've heard from people that Opus can be slow when using it for coding tasks. I've only been using Sonnet, and it's performed well enough for my purposes.

Sonnet works fine in many cases. Opus is smarter, and custom 'agents' can be set to use either.

I prefer configuring it to use Sonnet for things that don't require much reasoning/intelligence, with Opus as the coordinator.

Re: Claude Opus 4.1

#223

Post by mark_undoio »

rapind wrote: post #205
monatron wrote: post #32

Earlier quoted context omitted.

This is a great use case for sub-agents IMO. By default, sub-agents use sonnet. You can have opus orchestrate the various agents and get (close to) the best of both worlds.

In this case I don't think the controller needs to be the smartest model. I use sonnet as the main driver and pass the heavy thinking (via zen mcp) onto Gemini pro for example, but I could use openai or opus or all of them via OpenRouter. Subagents seem pretty similar to using zen mcp w/ OpenRouter but maybe better or at least more turnkey? I'll be checking them out.

Amp (ampcode.com) uses Sonnet as its main model and has GPT o3 as a special purpose tool / subagent. It can call into that when it needs particularly advanced reasoning.

Interestingly I found that prompting it to ask the o3 submodel (which they call The Oracle) to check Sonnet's working on a debugging solution was helpful. Extra interesting to me was the fact that Sonnet appeared to do a better job once I'd prompted that (like chain of thought prompting, perhaps asking it to put forward an explanation to be checked actually triggered more effective thinking).

Re: Claude Opus 4.1

#224

Post by sothatsit »

jzig wrote: post #10

I'm confused by how Opus is presented to be superior in nearly every way for coding purposes yet the general consensus and my own experience seem to be that Sonnet is much much better. Has anyone switched to entirely using Opus from Sonnet? Or maybe switching to Opus for certain things while using Sonnet for others?

Opus really shines for completing long-running tasks with no supervision. But if you are using Claude Code interactively and actively steering it yourself, Sonnet is good enough and is faster.

I don't believe anyone saying Sonnet yields better results than Opus though, as my experience has been exactly the opposite. But trade-off wise, I can definitely see it being a better experience when used interactively because of its speed and lower cost.

Re: Claude Opus 4.1

#225

Post by dnh44 »

rapind wrote: post #204
torginus wrote: post #147

Earlier quoted context omitted.

I think this means that GPT5 is better - you can't launch a worse model after the competitor supersedes you - you have to show that you're in the lead even if its just for a day.

Not sure that this is true. Are there a lot of people waiting anxiously to adopt the next model on the day of release and expecting some huge work advantage?

If you’re using an LLM near the limits of what it can do then a small improvement in performance is noticeable.

Re: Claude Opus 4.1

#226

Post by 47282847 »

Filligree wrote: post #69
ryandrake wrote: post #60

Am I the only one super confused about how to even get started trying out this stuff? Just so I wouldn't be "that critic who doesn't try the stuff he criticizes," I tried GitHub Copilot and was kind of not very impressed. Someone on HN told me Copilot sucks, use Claude. But I have no idea what the right way to do it is because there are so many paths to choose. Let's see: we have Claude Code vs. Claude the API vs. Cl…

You need Claude Pro or Max. The website subscription also allows you to use the command line tool—the rate limits are shared—and the command line tool includes IDE integration, at least for VSCode. Claude Code is currently best-in-class, so no point in starting elsewhere, but you do need to read the documentation.

> You need Claude Pro or Max.

Actually, to try it out, prepaid token billing is fine. You are not required to have a subscription for claude code cli. Even just $5 gave me enough breathing room to get a feeling for its potential, personally. I do not touch code often these days so I was relieved not to have to subscribe and cancel again just to play around a little and have it write some basic scripts for me.

Re: Claude Opus 4.1

#227

Post by andyferris »

bananapub wrote: post #134
mocmoc wrote: post #96

Their limits are just … a real road blocker

huh? Claude Mad is tens of hours of opus a month, or you can pay per token and have unlimited. Or did you mean “I wish it was cheaper”?

Ha - the $200 plan should be renamed to "Claude Mad Max" :)

Re: Claude Opus 4.1

#228

Post by trenchpilgrim »

jstummbillig wrote: post #197
bdamm wrote: post #180

Earlier quoted context omitted.

I've been having a great time with Windsurf's "Planning" feature. Have a nice discussion with Cascade (Claude) all about what it is that neerds to happen - sometimes a very long conversation including test code. Then when everything is very clear, make it happen. Then test and debug the results with all that context. Pretty nice.

Can you explain what you do exactly? Do you enable plan mode and use with chat...?

In Zed I switch the AI panel to ask mode and chat with the agent about different approaches and have it draft patches. Then when I think there's a design worth trying, switch to Write mode and have it implement that change + run the tests and diagnostics to verify the code at least compiles, tests pass and follows our style guides. Finally a line by line review + review of the test coverage (in terms of interface surface area) before submitting a PR for another human review.

Re: Claude Opus 4.1

#229

Post by paulryanrogers »

Etheryte wrote: post #107
qsort wrote: post #5

All three major labs released something within hours of each other. This anime arc is insane.

This is why you have PR departments. Being on top of the HN front page, news sites, etc matters a lot. Even if you can't be the first, it's important to dilute the attention as much as possible to reduce the limelight your competitors get.

"Prep the next three point releases now, but don't release any until I say so. None needs to be noticably better or even different, just has to have a higher number." -CEO of AI companies
Post reply on HN