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

401–410 of 822 posts

Re: Claude Sonnet 5

#401

Post by XCSme »

XCSme wrote: post #400
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.

Well, it is a Sonnet model, it is indeed better[0] than Sonnet 4.6 (smarter, faster, cheaper), but I don't see why would you use it as opposed to Opus 4.8 low or GLM-5.2... [0]: https://aibenchy.com/compare/anthropic-claude-sonnet-4-6-med...

What's interesting, is that Sonnet 5 is actually worse[0] than 4.6 without reasoning.

It makes some sense, as models are trained more and more with reasoning, than without.

[0]: https://aibenchy.com/compare/anthropic-claude-sonnet-4-6-non...

Re: Claude Sonnet 5

#402

Post by girvo »

lucamark wrote: post #220
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.

You're referring to the Agentic search, but if you look at the Agentic computer use the cost is basically halved. However, I am also confused about market positioning. Too expensive to perform daily tasks - open souce models are much cheaper - and not frontier model to address complex real world problems. Rarely used Sonnet btw.

The specific market positioning is... for me to use at my big tech company job, where we aren't allowed to use GLM and similar, but have fixed caps on how much token usage we're allowed to rack up a month.

Re: Claude Sonnet 5

#403

Post by pixl97 »

EddieRingle wrote: post #331
everforward wrote: post #159

Earlier quoted context omitted.

There’s no way to justify their valuations if they get downgraded to a pair programming tool. They need fully agentic stuff to work and replace human engineers to even come close. Offhand, I’m not even certain whether a model like that could justify the constant retraining we’re doing on the agentic models. It doesn’t make a lot of sense to spend millions or billions on training to reduce hallucinations by 0.3% if yo…

> There’s no way to justify their valuations if they get downgraded to a pair programming tool. Honestly I still don't see how they justify their valuations, period. If anything they're serious liabilities. Open-weight models are improving and reaching "good enough" levels for more and more tasks. They're also known quantities; you know what you're getting with them and don't have to worry about the model silently (o…

>Open-weight models are ...

Not the first one to come up with that likely outcome either. I mean, if you're being restricted from SOTA models now, how long do you expect before the FBI kicks in your door for using an 'illegal' open model?

Re: Claude Sonnet 5

#404

Post by botfriendsarent »

Sonnet 5 OUCH! every model is just loaded with more hurt, stolen content, BS prompts, more scare tactics, more illusions, more government lobbying, less honesty.

Oh Claude you master of software engineering does it ever end? DO you have no bounds?

How may we further assist you oh Claude?

Re: Claude Sonnet 5

#406

Post by NonHyloMorph »

pennomi wrote: post #65
Sol- wrote: post #45

Wonder if the whole cyber paranoia leads to their models ultimately generating less secure code. After all, if it has the ability to generate safe code, it would imply that it knows something about cybersecurity, which could surely be used to hack all the banks in the world.

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.

Interesting, you find that in medieval painting, due to the authority of the catholic church.

Re: Claude Sonnet 5

#408

Post by nolok »

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.

Same boat as you, and my answer is "... Except when I ask and overall or checkup task that is specifically heavy or overseeing in which case I use the maximum level" which lately meant ultracode.

I'm not going to play around with thinking level every request because the goal is to make me save time not spend it in a different setting menu.

Re: Claude Sonnet 5

#409

Post by energy123 »

jsnell wrote: post #386
energy123 wrote: post #369

Earlier quoted context omitted.

> by definition the entire frontier would be occupied by Opus. But the entire frontier is occupied by Opus under any reasonable interpolation scheme (piecewise linear which is what they've done, and most reasonable spline or polynomial fits would also lead to the same result) over the overlapping x values for which both are defined. Under that interpolation scheme, for x > ($ cost of Opus low effort), Opus is Pareto-…

I really don't get what you're proposing. The cost ranges do not overlap at the low end. You can't (by definition!) interpolate outside of the range. If you mean extrapolate, at that point you're just making up data. The available effort levels are discrete and covered totally by the benchmarks. You can draw on the monitor with a sharpie to show a "ultra-low" effort level for Opus that scores better than Sonnet "low"…

That's why I said "over the shared frontier" in my first post and more precisely in my second post I said "over the overlapping x values for which both are defined."

It was a claim that applies to a range of x-values where both curves are defined.

Of course if you go beyond those x-values where only one of the two are defined, then trivially the one that is defined constitutes the Pareto frontier in that region. Which is what I understand to be your point?

Re: Claude Sonnet 5

#410

Post by atemerev »

bjelkeman-again wrote: post #381
atemerev wrote: post #179

Earlier quoted context omitted.

Well, the weights are open. De-CCP-ing them is a trivial task, about 40 minutes on modern hardware. So can be done for about $50.

Any good reference for how?

https://github.com/AUGMXNT/deccp - one example for Qwen models. For GLM 5.2, abliteration/realignment works somewhat differently, but with Claude's help, you can finish the job.

I am planning to release the steering patch for the GLM 5.2 eliminating pro-CCP alignment in the next few days.

Post reply on HN