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

Claude Sonnet 5

anthropic.com

Post reply on HN
Print view View original

471–480 of 822 posts

Re: Claude Sonnet 5

#471

Post by windexh8er »

doctoboggan wrote: post #29

The cost per task chart is telling me that I should _never_ use Sonnet 5 above medium effort level - Opus always performs better for a given cost. So I guess the takeaway is that if Sonnet 5 medium isn't good enough for you, switch models, not effort levels.

Except for the fact that Opus 4.8 is not good. Constant hallucinations, doesn't use the web very intentionally until you explicitly ask it to and it nopes out rather quick on benign items. Anthropic has been very disappointing as of late. All of the gatekeeping is taking a toll on what should be some of the better models out there, but you can't trust 4.8 to go off on its own. It will burn down tokens doing what it deems correct as per its guidance. Truly painful to use.

Re: Claude Sonnet 5

#472

Post by lukan »

windexh8er wrote: post #471
doctoboggan wrote: post #29

The cost per task chart is telling me that I should _never_ use Sonnet 5 above medium effort level - Opus always performs better for a given cost. So I guess the takeaway is that if Sonnet 5 medium isn't good enough for you, switch models, not effort levels.

Except for the fact that Opus 4.8 is not good. Constant hallucinations, doesn't use the web very intentionally until you explicitly ask it to and it nopes out rather quick on benign items. Anthropic has been very disappointing as of late. All of the gatekeeping is taking a toll on what should be some of the better models out there, but you can't trust 4.8 to go off on its own. It will burn down tokens doing what it d…

"but you can't trust 4.8 to go off on its own."

And what (avaiable) model do you trust to go off on its own?

Re: Claude Sonnet 5

#473

Post by breezybottom »

pigpop wrote: post #301
WhyIsItAlwaysHN wrote: post #272

Earlier quoted context omitted.

There is no nefariousness in owning all the means of production, it's the endgame of maximizing profit. However the result is exactly the same, concentration of power.

This is such a defeatist and low agency take. "means of production" are not a limited resource like gold that you have to extract from natural sources or divvy up. They are fundamentally skill and knowledge that anyone can attain and put to use, maybe not on the same scale as a well funded business but even those businesses had to start somewhere in order to grow to the size they are now. So rather than casting asper…

You think AI tech doesn't use rare earth metals?

Re: Claude Sonnet 5

#474

Post by BoorishBears »

raincole wrote: post #425
pennomi wrote: post #65

Earlier quoted context omitted.

Trying to censor nudity in image generation models caused all kinds of problems with anatomy in image models. I’m sure these models will have similar issues with security.

Censorship on image generation models works on another level. The models can generate NSFW, but there are extra computer vision models checking if the images can be shown to the users. It's especially obvious for Grok and ChatGPT.

There are image models with censorship at every stage from pretraining to posttraining.

Most recently Ideogram released an open weight model that will denoise into a grey image with the text "Blocked by safety filter" notice for certain prompts

Of course, because it's open weights people have found defeats

Re: Claude Sonnet 5

#475

Post by fractorial »

brunooliv wrote: post #278

I only wish Opus 4.6 from earlier this year at a faster inference speed. Since Opus 4.6 things have been so much messier and the overall push for more agency isn’t really panning out for agent assisted development as much as they would like

I still use Opus 4.6 (with later models for subagents only sometimes), but I have been preparing for it to go away.

Re: Claude Sonnet 5

#476

Post by easygenes »

matheusmoreira wrote: post #437
AquinasCoder wrote: post #138

Earlier quoted context omitted.

While I appreciate, they publish this information, it's increasingly hard to keep track of it all. I've lost the mental model of how different models at different effort levels perform and what tasks they are good at. In practice, I tend to just use the default on Claude Code that works well enough. But I wonder to what degree other users really play around with these settings to optimize for their project.

I always use Opus 4.8 at max effort for everything. The $20 subscription didn't have enough tokens, but the $100 one had too many of them. So now I just max out Opus in order to maintain 100% weekly utilization.

I'm a heavy enough user that I have both the OAI and Anth $200 plans. I always use at least 50% of my weekly Opus quota at Extra setting (meaning I use double the limit of the $100 plan, at minimum). Max I rarely touch because it is twice as slow and the incremental capability gain is minimal. Usually if Opus can't sort something well at Extra, the answer isn't to use Max but to hand the issue off to GPT-5.5 at XHigh.

Re: Claude Sonnet 5

#477

Post by nl »

sanderjd wrote: post #195
AquinasCoder wrote: post #138

Earlier quoted context omitted.

While I appreciate, they publish this information, it's increasingly hard to keep track of it all. I've lost the mental model of how different models at different effort levels perform and what tasks they are good at. In practice, I tend to just use the default on Claude Code that works well enough. But I wonder to what degree other users really play around with these settings to optimize for their project.

What I want is a harness that knows how to optimize this kind of thing for me.

In practice I don't think any harness (happy to be corrected here!) uses the lesser capability models for writing code. The cost trade-offs are rarely worth it.

They are often used for reading code though.

To expand on this, while the "big model to write a plan, small model to write the specific code" idea is quite common it trips up on edge cases.

In theory the flow works like this:

- small fast models read lots of code, and pass details to the large model to write a plan

- large model takes those details and writes a detailed plan

- medium models write the code

The issue happens when the medium model hits something that the plan didn't take into account (which happens a lot - the big model didn't actually read the code). Then it has to either guess, or pass back to the large model.

If it guesses, the plan usually starts to fall to bits.

If it passes back to the large model, inevitable the large model has to start reading lots of code. In that case you are paying the expensive tokens to read so you might as well have it write the code too (many less tokens are written than are read)

It might be possible to get this to work, but I haven't seen anyone who has tried agentic work with frontier models be satisfied with this hybrid setup.

I'd note that Amp (mentioned above) is probably the leader in using multiple providers in a coding agent but still uses frontier models to write code.

Re: Claude Sonnet 5

#478

Post by deadbabe »

AquinasCoder wrote: post #138
doctoboggan wrote: post #29

The cost per task chart is telling me that I should _never_ use Sonnet 5 above medium effort level - Opus always performs better for a given cost. So I guess the takeaway is that if Sonnet 5 medium isn't good enough for you, switch models, not effort levels.

While I appreciate, they publish this information, it's increasingly hard to keep track of it all. I've lost the mental model of how different models at different effort levels perform and what tasks they are good at. In practice, I tend to just use the default on Claude Code that works well enough. But I wonder to what degree other users really play around with these settings to optimize for their project.

There are token optimization consultants that can help organizations find the right balance of models for their employees to minimize costs.

Re: Claude Sonnet 5

#479

Post by ashvardanian »

Got really excited for this model and asked my Opus planners in 3 pretty different projects to use Sonnets instead of Opus subagents to help me experiment on HPC kernels faster. Not one of them ended up writing a single line of code... Sonnets just kept spinning, wasting tokens. Can't remember the last time it happened with Opus in my codebases. Reverting back.

Re: Claude Sonnet 5

#480

Post by bel8 »

simonw wrote: post #399

Claude Sonnet 5 itself described its pelican as looking like a goose: > Illustration of a white goose riding a bicycle, with one wing extended forward to grip the handlebar, set against a plain white background with a brown ground line. https://simonwillison.net/2026/Jun/30/claude-sonnet-5/

That's possibly the worst pelican I saw from all recent LLMs.

Meanwhile GLM 5.2 drew a cool self-contained fully animated SVG pelican:

https://simonwillison.net/2026/Jun/17/glm-52

Post reply on HN