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

371–380 of 525 posts

Re: Claude Opus 4.5

#371

Post by nickandbro »

I use the following models like so nowadays:

Gemini is great, when you have gitingested the code of pypi package and want to use it as context. This comes in handy for tasks and repos outside the model's training data.

5.1 Codex I use for a narrowly defined task where I can just fire and forget it. For example, codex will troubleshoot why a websocket is not working, by running its own curl requests within cursor or exec'ing into the docker container to debug at a level that would take me much longer.

Claude 4.5 Opus is a model that I feels trustworthy for heavy refactors of code bases or modularizing sections of code to become more manageable. Often it seems like the model doesn't leave any details out and the functionality is not lost or degraded.

Re: Claude Opus 4.5

#372

Post by dcre »

koolala wrote: post #320
throwuxiytayq wrote: post #144

Earlier quoted context omitted.

y’all hallucinating harder than GPT2 on DMT

Do you not believe that Intelligence Throttling exists what-so-ever? It's a lot like overworking a person in real life with too many tasks at once except its a supercomputer.

I do not believe it exists.

Re: Claude Opus 4.5

#373

Post by simonw »

tkgally wrote: post #362
simonw wrote: post #100

Notes and two pelicans: https://simonwillison.net/2025/Nov/24/claude-opus/

I added Opus 4.5 to my benchmark of 30 alternatives to your now-classic pelican-bicycle prompt (e.g., “Generate an SVG of a dragonfly balancing a chandelier”). Nine models are now represented: https://gally.net/temp/20251107pelican-alternatives/index.ht...

I hadn't seen these before, they are so cool! Definitely enhances the idea to see a bunch of different illustrations in the same place.

Blogged about it here: https://simonwillison.net/2025/Nov/25/llm-svg-generation-ben...

Re: Claude Opus 4.5

#374

Post by meowface »

BoorishBears wrote: post #176
nostrademons wrote: post #163

Earlier quoted context omitted.

Why? They just closed a $13B funding round. Entirely possible that they're selling below-cost to gain marketshare; on their current usage the cloud computing costs shouldn't be too bad, while the benefits of showing continued growth on their frontier models is great. Hell, for all we know they may have priced Opus 4.1 above cost to show positive unit economics to investors, and then drop the price of Opus 4.5 to spur…

Eh, I'm testing it now and it seems a bit too fast to be the same size, almost 2x the Tokens Per Second and much lower Time To First Token. There are other valid reasons for why it might be faster, but faster even while everyone's rushing to try it at launch + a cost decrease leaves me inclined to believe it's a smaller model than past Opus models

It does seem too fast to be a huge model, but it also is giving me the vibes of the typical Opus level of intelligence. So who knows.

Re: Claude Opus 4.5

#375

Post by brianjking »

tekacs wrote: post #60
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…

This is also super relevant for everyone who had ditched Claude Code due to limits: > For Claude and Claude Code users with access to Opus 4.5, we’ve removed Opus-specific caps. For Max and Team Premium users, we’ve increased overall usage limits, meaning you’ll have roughly the same number of Opus tokens as you previously had with Sonnet. We’re updating usage limits to make sure you’re able to use Opus 4.5 for daily…

They also reset limits today, which was also quite kind as I was already 11% into my weekly allocation.

Re: Claude Opus 4.5

#376

Post by alphabettsy »

idonotknowwhy wrote: post #277
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,…

Glad you mentioned "Cursor has been a terrible experience lately", as I was planning to finally give it a try. I'd heard it has the best auto-complete, which I don't get use VSCode with Claude Code in the terminal.

You should still give it a try. Can’t speak for their experience, but doesn’t ring true for me.

Re: Claude Opus 4.5

#377

Post by sothatsit »

nojs wrote: post #342
simonw wrote: post #100

Notes and two pelicans: https://simonwillison.net/2025/Nov/24/claude-opus/

> Thinking blocks from previous assistant turns are preserved in model context by default This seems like a huge change no? I often use max thinking on the assumption that the only downside is time, but now there’s also a downside of context pollution

Opus 4.5 seems to think a lot less than other models, so it’s probably not as many tokens as you might think. This would be a disaster for models like GPT-5 high, but for Opus they can probably get away with it.

Re: Claude Opus 4.5

#378

Post by chrisweekly »

pertymcpert wrote: post #234
chrisweekly wrote: post #126

Earlier quoted context omitted.

Any experience w/ Haiku-4.5? Your "heavy Claude code user" and "speed" comment gave me hope you might have insights. TIA

Not GP but my experience with Haiku-4.5 has been poor. It certainly doesn't feel like Sonnet 4.0 level performance. It looked at some python test failures and went in a completely wrong direction in trying to address a surface level detail rather than understanding the real cause of the problem. Tested it with Sonnet 4.5 and it did it fine, as an experienced human would.

Thanks!

Re: Claude Opus 4.5

#379

Post by jiggawatts »

jammaloo wrote: post #142
jiggawatts wrote: post #111

Earlier quoted context omitted.

I recently wrote a small CLI tool for scanning through legacy codebases. For each file, it does a light parse step to find every external identifier (function call, etc...), reads those into the context, and then asks questions about the main file in question. It's amazing for trawling through hundreds of thousands of lines of code looking for a complex pattern, a bug, bad style, or whatever that regex could never ho…

Is there any chance you'd be willing to share that tool? :)

It's a mess vibe coding combined with my crude experiments with the new Microsoft Agent Framework. Not something that's worth sharing!

Also, I found that I had to partially rewrite it for each "job", because requirements vary so wildly. For example, one customer had 200K lines of VBA code in an Access database, which is a non-trivial exercise to extract, parse, and cross-reference. Invoking AI turned out to be by far the simplest part of the whole process! It wasn't even worth the hassle of using the MS Agent Framework, I would have been better off with plain HTTPS REST API calls.

Re: Claude Opus 4.5

#380

Post by Uehreka »

Wowfunhappy wrote: post #187
ceejayoz wrote: post #185

Earlier quoted context omitted.

There's a reason they're called "guidelines" and not "hard rules".

I thought the reminder from GP was fair and I'm disappointed that it's downvoted as of this writing. One thing I've always appreciated about this community is that we can remind each other of the guidelines. Yes it was just one word, and probably an accident—an accident I've made myself, and felt bad about afterwards—but the guideline is specific about "word or phrase", meaning single words are included. If GGP's sin…

I’m not the GP, but the reason I capitalize words instead of italicizing them is because the italics don’t look italic enough to convey emphasis. I get the feeling that that may be because HN wants to downplay emphasis in general, which if true is a bad goal that I oppose.

Also, those guidelines were written in the 2000s in a much different context and haven’t really evolved with the times. They seem out of date today, many of us just don’t consider them that relevant.

Post reply on HN