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

Claude Opus 4.5

anthropic.com

Post reply on HN
Print view View original

411–420 of 525 posts

Re: Claude Opus 4.5

#411

Post by paradite »

bgrainger wrote: post #205
mritchie712 wrote: post #55

Earlier quoted context omitted.

> only Claude Code has been able to really solve; Sonnet 4.5 in there consistently performs better than Sonnet 4.5 anywhere else. I think part of it is this[0] and I expect it will become more of a problem. Claude models have built-in tools (e.g. `str_replace_editor`) which they've been trained to use. These tools don't exist in Cursor, but claude really wants to use them. 0 - https://x.com/thisritchie/status/1944038…

This feels like a dumb question, but why doesn't Cursor implement that tool? I built my own simple coding agent six months ago, and I implemented str_replace_based_edit_tool ( https://platform.claude.com/docs/en/agents-and-tools/tool-us... ) for Claude to use; it wasn't hard to do.

Maybe they want to have their own protocol and standard for file editing for training and fine-tuning their own models, instead of relying on Anthropic standard.

Or it could be a sunk cost associated with Cursor already having terabytes of training data with old edit tool.

Re: Claude Opus 4.5

#412

Post by IgorPartola »

brianjking wrote: post #382
IgorPartola wrote: post #311

Earlier quoted context omitted.

For me this is sub agent usage. If I ask Claude Code to use 1-3 subagents for a task, the 5 hour limit is gone in one or two rounds. Weekly limit shortly after. They just keep producing more and more documentation about each individual intermediate step to talk to each other no matter how I edit the sub agent definitions.

Care sharing some of your sub-agent usage? I've always intended to really make use of them, but with skills, I don't know how I'd separate these in many use cases?

I just grabbed a few from here: https://github.com/VoltAgent/awesome-claude-code-subagents

Had to modify them a bit, mostly taking out the parts I didn’t want them doing instead of me. Sometimes they produced good results but mostly I found that they did just as well as the main agent while being way more verbose. A task to do a big hunt or to add a backend and frontend feature using two agents at once could result in 6-8 sizable Markdown documents.

Typically I find that just adding “act as a Senior Python engineer with experience in asyncio” or some such to be nearly as good.

Re: Claude Opus 4.5

#413

Post by zsoltkacsandi »

thomasfromcdnjs wrote: post #389
zsoltkacsandi wrote: post #253

Earlier quoted context omitted.

I did not say that I only ran the prompt once per attempt. When I say that second time it failed it means that I spent hours to restart, clear context, giving hints, everything to help the model to produce something that works.

You are really speaking to others points. Get a friend of yours to read what you are saying, it doesn't sound scientific in the slightest.

I never claimed this was a scientific study. It was an observation repeated over time. That is empirical in the plain meaning of the word.

Criticizing it for “not being scientific” is irrelevant, I didn’t present it as science. Are people only allowed to share experiences here if they come wrapped in a peer-reviewed paper?

If you want to debate the substance of the observation, happy to. But don’t rewrite what I said into a claim I never made.

Re: Claude Opus 4.5

#414

Post by fabbbbb »

versteegen wrote: post #330
Wowfunhappy wrote: post #318

Earlier quoted context omitted.

But again, if that is what the guideline is referring to, why does it say "If you want to emphasize a _word or phrase_". By my reading, it is quite explicitly including single words!

Imagine I capitalised a whole selection of specific words in this sentence for emphasis, how annoying that would be to read. I'll spare you. That is what the guideline is about, not one single instance.

Which exact part of the guideline makes you think so?

Re: Claude Opus 4.5

#415

Post by ACCount37 »

ewoodrich wrote: post #252
baq wrote: post #248

Earlier quoted context omitted.

This isn’t how you should be benchmarking models. You should give it the same task n times and see how often it succeeds and/or how long it takes to be successful (see also the 50% time horizon metric by METR).

I was pretty disappointed to learn that the METR metric isn't actually evaluating a model's ability to complete long duration tasks. They're using the estimated time a human would take on a given task. But it did explain my increasing bafflement at how the METR line keeps steadily going up despite my personal experience coding daily with LLMs where they still frequently struggle to work independently for 10 minutes w…

It makes perfect sense to use human times as a baseline. Because otherwise, the test would be biased towards models with slower inference.

If model A generates 10 tokens a second and model B generates 100 tokens a second, then using real LLM inference time puts A at a massive 10x advantage, all other things equal.

Re: Claude Opus 4.5

#416

Post by Huppie »

fabbbbb wrote: post #278
HugoDias wrote: post #76

Earlier quoted context omitted.

TIL! I'll finally give Claude Code a try. I've been using Cursor since it launched and never tried anything else. The terminal UI didn't appeal to me, but knowing it has better performance, I'll check it out. Cursor has been a terrible experience lately, regardless of the model. Sometimes for the same task, I need to try with Sonnet 4.5, ChatGPT 5.1 Codex, Gemini Pro 3... and most times, none managed to do the work,…

I get the same impression. Even GPT 5.1 Codex is just sooo slow in Cursor. Claude Code with Sonnet is still the benchmkar. Fast and good.

I was evaluating codex vs claude code the past month and GPT 5.1 codex being slow is just the default experience I had with it.

The answers were mostly on par (though different in style which took some getting used to) but the speed was a big downer for me. I really wanted to give it an honest try but went back to Claude Code within two weeks.

Re: Claude Opus 4.5

#417

Post by paul_sutyrin »

adonese wrote: post #383
config_yml wrote: post #53

Earlier quoted context omitted.

I use plan mode in claude code, then use gpt-5 in codex to review the plan and identify gaps and feed it back to claude. Results are amazing.

I was doing this but I got worried I will lose touch with my critical thinking (or really just thinking for that matter). As it was too easy to just copy paste and delegate the thinking to The Oracle.

Of course the Great Elephant of Postgres should do the thinking! And it is, as known, does not forget anything...

Re: Claude Opus 4.5

#418

Post by aurareturn »

dave1010uk wrote: post #249

The Claude Opus 4.5 system card [0] is much more revealing than the marketing blog post. It's a 150 page PDF, with all sorts of info, not just the usual benchmarks. There's a big section on deception. One example is Opus is fed news about Anthropic's safety team being disbanded but then hides that info from the user. The risks are a bit scary, especially around CBRNs. Opus is still only ASL-3 (systems that substantia…

  Pages 22–24 of Opus’s system card provide some evidence for this. Anthropic run a multi-agent search benchmark where Opus acts as an orchestrator and Haiku/Sonnet/Opus act as sub-agents with search access. Using cheap Haiku sub-agents gives a ~12-point boost over Opus alone.
Will this lead to another exponential in capabilities and token increase in the same order as thinking models?

Re: Claude Opus 4.5

#419

Post by anon7000 »

Wowfunhappy wrote: post #246
davidsainez wrote: post #242

Earlier quoted context omitted.

There are well documented cases of performance degradation: https://www.anthropic.com/engineering/a-postmortem-of-three-... . The real issue is that there is no reliable system currently in place for the end user (other than being willing to burn the cash and run your own benchmarks regularly) to detect changes in performance. It feels to me like a perfect storm. A combination of high cost of inference, extreme compe…

> There are well documented cases of performance degradation: https://www.anthropic.com/engineering/a-postmortem-of-three-... There was one well-documented case of performance degradation which arose from a stupid bug, not some secret cost cutting measure.

> some secret cost cutting measure

That’s not the point — it’s just a day in the life of ops to tweak your system to improve resource utilization and performance. Which can cause bugs you don’t expect in LLMs. it’s a lot easier to monitor performance in a deterministic system, but harder to see the true impact a change has to the LLM

Re: Claude Opus 4.5

#420

Post by delaminator »

burgerone wrote: post #235
llamasushi wrote: post #30

The burying of the lede here is insane. $5/$25 per MTok is a 3x price drop from Opus 4. At that price point, Opus stops being "the model you use for important things" and becomes actually viable for production workloads. Also notable: they're claiming SOTA prompt injection resistance. The industry has largely given up on solving this problem through training alone, so if the numbers in the system card hold up under a…

Using AI in production is no doubt an enormous security risk...

Not all production processes untrusted input.
Post reply on HN