Claude Sonnet 5 • Hacker News Board

Re: Claude Sonnet 5

#441

Post by c0m47053 » Tue, Jun 30, 2026, 10:39 PM UTC

Jcampuzano2 wrote: post #216

I'm struggling to understand why I'd ever use this instead of just using a lower effort level for opus given on many of the benchmarks listed the cost per task rises above opus at anything higher than medium effort. Only thing I can think of is for when someone is out of opus credits. Of course there are API billing use cases but I'd probably still just use opus on low.

Specific task based benchmarks don't reflect a lot of day to day agentic use cases in my experience. If you are working on a series of discrete tasks and can clear context after each one and move to the next, you might get that sort of efficiency from Opus low effort. I often find that when working through a real problem, iterating and discovering, context length can creep up, and that is where opus tends to get expensive.

Re: Claude Sonnet 5

#442

Post by ATMLOTTOBEER » Tue, Jun 30, 2026, 10:41 PM UTC

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.

Agreed I think your strategy is optimal. This is what I landed on as well

Re: Claude Sonnet 5

#443

Post by secretslol » Tue, Jun 30, 2026, 10:41 PM UTC

kube-system wrote: post #254

secretslol wrote: post #86

Earlier quoted context omitted.

"Lower ability to perform cybersecurity-related tasks" makes me super concerned it will leave my codebase like Swiss cheese for any American granny with access to Fable 5, when we non-American Brits, or rest-of-worlders, don't have access to it to clean our codebases.

> any American granny with access to Fable 5, Fable is effectively not available to the general public in the US either

True, but Trump & Co. did give them permission to let Americans continue using it, but Anthropic turned that down (for now at least...).

Re: Claude Sonnet 5

#444

Post by MagicMoonlight » Tue, Jun 30, 2026, 10:46 PM UTC

itopaloglu83 wrote: post #245

Jcampuzano2 wrote: post #216

I'm struggling to understand why I'd ever use this instead of just using a lower effort level for opus given on many of the benchmarks listed the cost per task rises above opus at anything higher than medium effort. Only thing I can think of is for when someone is out of opus credits. Of course there are API billing use cases but I'd probably still just use opus on low.

More and more I find myself trying to stop Opus from doing something stupid, and at every turn I need to tell it to stop overcomplicating things. I think the models are being optimized for wealth extraction from users and companies, instead of solving problems. I don't know why Opus would try to create an entire library when I told it specifically to do something simple that would take 2-3 lines of Python.

[dead]

Re: Claude Sonnet 5

#445

Post by matheusmoreira » Tue, Jun 30, 2026, 10:47 PM UTC

secretslol wrote: post #86

satvikpendem wrote: post #26

> Evaluations also show that it has a much lower ability to perform cybersecurity tasks than our current Opus models. Why would they brag about something like this? It's like they know people want to use models to perform cybersecurity tasks yet knowingly deny them the ability. And Opus 4.8 is still cheaper for a higher pass rate (much less open weight models like GLM 5.2) so not sure why I'd use Sonnet except on the…

"Lower ability to perform cybersecurity-related tasks" makes me super concerned it will leave my codebase like Swiss cheese for any American granny with access to Fable 5, when we non-American Brits, or rest-of-worlders, don't have access to it to clean our codebases.

That's the literal mission of the NSA. Security and strong cryptography for the US while everyone else gets "export grade" nonsense.

Re: Claude Sonnet 5

#446

Post by HDBaseT » Tue, Jun 30, 2026, 10:47 PM UTC

baq wrote: post #157

satvikpendem wrote: post #105

Earlier quoted context omitted.

Due to Dario hyping it up as a world ending model. If they kept their mouths shut we'd all have it now still.

Where is gpt 5.6?

GPT 5.6 exists, just not for you and me.

Everyone dislikes when these models are provided for use by the Department of Defense, but we can likely assume these newer, more capable models are being used by the NSA, FBI, CIA and other Five Eyes agencies to develop more backdoors, hack into more things to spy on us all.

We get drip fed the weaker models, but only once all the 0days have been used against us.

Re: Claude Sonnet 5

#447

Post by WorldPeas » Tue, Jun 30, 2026, 10:49 PM UTC

XCSme wrote: post #388

I just tested it on my benchmarks[0], it's GLM-5.2 level, at 2x cost, but also 2x faster. Weak spots (categories it fails): - Trivia — 0/3 - basically not much built-in knowledge - Combined tool-calling tasks — score 45/100, sometimes makes invalid tool calls - Puzzle Solving — score 77, flubs carwash-like tests [0]: https://aibenchy.com/compare/anthropic-claude-sonnet-4-6-med...

the (imperfect) comparison having used both for planning and execution is that GLM5.2 is too jumpy and eager to do things, often to a fault (e.g. deploying/using git when it shouldn't) while sonnet 5 was much lazier than any Claude model I have used has been, not adding an addendum to a plan that I asked for, then lying that it did when asked. Looking at the analysis[0] I don't think it's worth it for me. Maybe for others. Fable was certainly much better.

[0]: https://artificialanalysis.ai/models/claude-sonnet-5

Re: Claude Sonnet 5

#448

Post by Aeolun » Tue, Jun 30, 2026, 10:49 PM UTC

__natty__ wrote: post #365

itopaloglu83 wrote: post #245

Earlier quoted context omitted.

More and more I find myself trying to stop Opus from doing something stupid, and at every turn I need to tell it to stop overcomplicating things. I think the models are being optimized for wealth extraction from users and companies, instead of solving problems. I don't know why Opus would try to create an entire library when I told it specifically to do something simple that would take 2-3 lines of Python.

> More and more I find myself trying to stop Opus from doing something stupid, and at every turn I need to tell it to stop overcomplicating things Yeah, that’s my thoughts as well. I feel it’s great for benchmarks and some tasks while in other it tries to spend as much tokens as possible, tries to overcomplicate task and needs seconds or third round of steering that costs. With the scale Anthropic operates I bet it’s…

It’s really weird when you go to one of the open models and suddenly the same context window stretches nearly 3-4 times as long.

Re: Claude Sonnet 5

#449

Post by usef- » Tue, Jun 30, 2026, 10:49 PM UTC

Retr0id wrote: post #47

conradkay wrote: post #19

Wow, seems worse even on price/performance than GLM 5.2, which is only 744b parameters. From the system card: "On CyberGym vulnerability discovery, Claude Sonnet 5 is less capable than Sonnet 4.6, and far less capable than Opus 4.8 and Mythos 5 As with the other evaluations in this section, these results were achieved with all safeguards turned off. When run with our default mitigations, Sonnet 5 scored a 0 on CyberG…

Finally, a viable business strategy - sell security-oblivious code monkeys for cheap, then charge premium rates for agents capable of cleaning up the mess.

Judging by the events of recent weeks, I'm guessing the low cyber results are why they were allowed to release it

Re: Claude Sonnet 5

#450

Post by ianberdin » Tue, Jun 30, 2026, 10:53 PM UTC

Anthropic outsmarted everyone again.

They released Sonnet 5 with a temporary price reduction until August. Everyone was excited, but in reality, they increased the tokenizer size by 50%. As a result, the actual cost went up by 50%, they shifted everyone's attention to decrease.

Thus, Anthropic is raising prices but not telling anyone about it. Nobody is really aware of it. You go to the pricing page, the price looks the same. Yet people are actually paying 50% more.

Very shady marketing.

And of course they lie about 35% again. In reality with coding it is 50%.

UPD: I run playcode.io, so it’s my job test all models, their pricing, quality in order to provide best price/quality/speedy/reliability to non-techy.