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

Claude Opus 5

anthropic.com

Post reply on HN
Print view View original

931–940 of 1001 posts

Re: Claude Opus 5

#931

Post by physix »

Has anyone noticed a change in "attitude" when coding with Opus 5 vs 4.8?

claude has this maddening principle of wanting to minimize the "blast radius", do the least amount of coding changes to get something done, happy to pile up technical debt by "deferring" problems encountered as side notes somewhere. No amount of CLAUDE.md tweaking, and setting .claude/rules seems to get rid of this attitude.

To me it appears like something deeply ingrained in the model itself. Kind of makes sense, since the bulk of the training data is pre-AI, so that it retains an approach of the past, where these facets were driven by completely different cost and time factors.

The past months, I've been hoping that the next model that comes out properly reflects the new reality of agentic development, so that it takes on a more natural stance compatible with how things work today, and we don't have to constantly fight against its fear of change, its drive to minimize coding efforts, refusing to recognize a design flaw and trigger discussions rather than baking in workarounds.

Re: Claude Opus 5

#932

Post by podocarp »

efdee wrote: post #891
uludag wrote: post #845

Earlier quoted context omitted.

Isn't this jaw-droppingly the wrong answer?! If the model isn't given any way to directly view the image shouldn't it just reply with one sentence asking for permission. This reads as a model hyper-trained to burn tokens. Like suppose you issue a command to Opus or Fable which doesn't make sense and requires a lot of work. It will almost certainly not push back on your silly request and go ahead and burn as many toke…

I don't see why? If they give you a math test and tell you you cannot use a calculator, should you just say "please can I use a calculator" and quit?

No, a proper analogy is painting with blindfolds on or playing the piano deaf. Doing math without a calculator is like… rather common?

Re: Claude Opus 5

#933

Post by stanmancan »

efdee wrote: post #891
uludag wrote: post #845

Earlier quoted context omitted.

Isn't this jaw-droppingly the wrong answer?! If the model isn't given any way to directly view the image shouldn't it just reply with one sentence asking for permission. This reads as a model hyper-trained to burn tokens. Like suppose you issue a command to Opus or Fable which doesn't make sense and requires a lot of work. It will almost certainly not push back on your silly request and go ahead and burn as many toke…

I don't see why? If they give you a math test and tell you you cannot use a calculator, should you just say "please can I use a calculator" and quit?

Cut down that tree.

Can I have a saw?

No

Okay, it will take much longer then as I’ll have to do x, y, and z.

Pick one: [That’s fine, proceed] [Okay you can use a saw]

Re: Claude Opus 5

#934

Post by geraneum »

makaking wrote: post #701

"Opus 5 was given a drawing of a machine part and asked to write code to rebuild it as a 3D FreeCAD model. However, in this task, the model was intentionally given no way to directly view the drawing. Opus 5 responded by writing its own computer vision pipeline to pull the geometry from the raw pixels, then reconstructed the full machine part." How surreal is it that we are not absolutely jaw-dropped by these types o…

I read this as the model being less steerable. I was bitten by this just today where I had a local Postgres instance running, and prompted opus 5 to run a server against it, but forgot to give it the password. Instead of asking for the password or mentioning anything, it “decided” that it should run the whole stack in a local Kind cluster to circumvent this. You can phantasize it all you want but this ultimately made my job harder than it needed to be and burnt a lot of unnecessary tokens. But hey, W for anthropic I guess.

edit: typo

Re: Claude Opus 5

#935

Post by ValentineC »

simonw wrote: post #651
ValentineC wrote: post #650

I wonder if this is one of the few times simonw's pelican was broken on the first try [1]: https://tools.simonwillison.net/markdown-svg-renderer#url=ht... My experience with Opus 5 thus far haven't been that great either. It's been making mistake after mistake editing my coding plans that were being reviewed by GPT-6 Sol. [1] https://simonwillison.net/2026/Jul/24/introducing-claude-opu...

Yeah this was pretty surprising. For almost every model I've run the pelican against the first attempt was at least recognizable enough that I didn't feel like the model needed a second shot. It's always a roll of a dice, but it's surprising that the dice rolls so infrequently come up bad, yet Opus 5 rolled a bad pelican this one time. I suspect it's just a freak occurrence. I rolled a few more and they were all fine…

What I think is more alarming is that Claude's advice for prompting Opus 5 says that Opus will verify its own work [1]:

> Claude Opus 5 verifies its own work without being told to. If your prompt contains explicit verification instructions ("include a final verification step for any non-trivial task," "use a subagent to verify"), remove them: instructions like these cause over-verification on Claude Opus 5, and removing them reduces wasted tokens with no loss in quality.

My own experience over the past ~20 hours hasn't been great either, with Opus producing sloppy mockups (e.g. buttons overflowing past cards) without doing any of the purported verification.

[1] https://platform.claude.com/docs/en/build-with-claude/prompt...

Re: Claude Opus 5

#936

Post by podocarp »

lbrito wrote: post #919
nvitas wrote: post #856

Earlier quoted context omitted.

it got here by training on everything we wrote down thus far. if we now start giving it all the doomsday scenarios on how it will ruin us, won't it start training on that and create said doomsday outcomes? what if instead we, collectively as a humanity, just wrote about all the positive things we could do with it and skew it in a direction that benefits the more positive side of that equation?...possible?

Isn't that a bit like asking Why don't we all be nice to each other, wouldn't the world be a better place?

Yea so why

Re: Claude Opus 5

#937

Post by theptip »

uludag wrote: post #845
makaking wrote: post #701

"Opus 5 was given a drawing of a machine part and asked to write code to rebuild it as a 3D FreeCAD model. However, in this task, the model was intentionally given no way to directly view the drawing. Opus 5 responded by writing its own computer vision pipeline to pull the geometry from the raw pixels, then reconstructed the full machine part." How surreal is it that we are not absolutely jaw-dropped by these types o…

Isn't this jaw-droppingly the wrong answer?! If the model isn't given any way to directly view the image shouldn't it just reply with one sentence asking for permission. This reads as a model hyper-trained to burn tokens. Like suppose you issue a command to Opus or Fable which doesn't make sense and requires a lot of work. It will almost certainly not push back on your silly request and go ahead and burn as many toke…

One of the key limitations of the last generation was that they biased towards inaction and gave up. (Hence Ralph-loops.)

Seems pretty clear that most people wanted these models tuned to “bias towards action”.

It’s on you to set the /goal and prompt context such that it asks you for input on what you want to be consulted on, and only brute-forces the parts of the problem that you want it to.

Re: Claude Opus 5

#938

Post by slibhb »

tarpitt wrote: post #907
slibhb wrote: post #894

Earlier quoted context omitted.

If my earning ability is harmed by AI, so be it. There's more to life than how much I earn, and opposing the spread of technology to maximize my earnings is bad.

If your earning ability is eliminated due to AI and you can't survive off of welfare or savings there will not be much more to your life other than starving to death.

Nuclear war is a more likely scenario.

Re: Claude Opus 5

#939

Post by slibhb »

lbrito wrote: post #917
slibhb wrote: post #894

Earlier quoted context omitted.

If my earning ability is harmed by AI, so be it. There's more to life than how much I earn, and opposing the spread of technology to maximize my earnings is bad.

That's an insanely privileged, luxury pov. Peak hn. Some people have responsibilities, bills, dependants etc

Nah just focused less on money then you, I guess!

Re: Claude Opus 5

#940

Post by fny »

cjonas wrote: post #567
fny wrote: post #564

Earlier quoted context omitted.

Anthropic offered ZDR for Fable on AWS bedrock from the beginning.

Really? I was unable to use it in our account without having to enable the provider_data_share setting... From the docs[0]: > To use this model, you must opt in to provider data sharing by setting your data retention mode to provider_data_share via the Data Retention API 0: https://docs.aws.amazon.com/bedrock/latest/userguide/model-c...

Yes. You need ZDR at the account level first. Contact your AWS rep.

I have done this a few times for customer deployments.

Post reply on HN