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

Claude Sonnet 4.6

anthropic.com

Post reply on HN
Print view View original

301–310 of 1001 posts

Re: Claude Sonnet 4.6

#301

Post by OtomotO »

andrewchilds wrote: post #244

Many people have reported Opus 4.6 is a step back from Opus 4.5 - that 4.6 is consuming 5-10x as many tokens as 4.5 to accomplish the same task: https://github.com/anthropics/claude-code/issues/23706 I haven't seen a response from the Anthropic team about it. I can't help but look at Sonnet 4.6 in the same light, and want to stick with 4.5 across the board until this issue is acknowledged and resolved.

Definitely my experience as well.

No better code, but way longer thinking and way more token usage.

Re: Claude Sonnet 4.6

#302

Post by stronglikedan »

the_duke wrote: post #157
andsoitis wrote: post #77

I’m voting with my dollars by having cancelled my ChatGPT subscription and instead subscribing to Claude. Google needs stiff competition and OpenAI isn’t the camp I’m willing to trust. Neither is Grok. I’m glad Anthropic’s work is at the forefront and they appear, at least in my estimation, to have the strongest ethics.

An Anthropic safety researcher just recently quit with very cryptic messages , saying "the world is in peril"... [1] (which may mean something, or nothing at all) Codex quite often refuses to do "unsafe/unethical" things that Anthropic models will happily do without question. Anthropic just raised 30 bn... OpenAI wants to raise 100bn+. Thinking any of them will actually be restrained by ethics is foolish. [1] https:/…

Not to diminish what he said, but it sounds like it didn't have much to do with Anthropic (although it did a little bit) and more to do with burning out and dealing with doomscoll-induced anxiety.

Re: Claude Sonnet 4.6

#303

Post by leumon »

stevepike wrote: post #87

I'm a bit surprised it gets this question wrong (ChatGPT gets it right, even on instant). All the pre-reasoning models failed this question, but it's seemed solved since o1, and Sonnet 4.5 got it right. https://claude.ai/share/876e160a-7483-4788-8112-0bb4490192af This was sonnet 4.6 with extended thinking.

My locally running nemotron-3-nano quantized to Q4_K_M gets this right. (although it used 20k thought tokens before answering the question)

Re: Claude Sonnet 4.6

#304

Post by baalimago »

I don't see the point nor the hype for these models anymore. Until the price is reduced significantly, I don't see the gain. They've been able to solve most tasks just fine for the past year or so. The only limiting factor is price.

Re: Claude Sonnet 4.6

#305

Post by j45 »

andrewchilds wrote: post #244

Many people have reported Opus 4.6 is a step back from Opus 4.5 - that 4.6 is consuming 5-10x as many tokens as 4.5 to accomplish the same task: https://github.com/anthropics/claude-code/issues/23706 I haven't seen a response from the Anthropic team about it. I can't help but look at Sonnet 4.6 in the same light, and want to stick with 4.5 across the board until this issue is acknowledged and resolved.

I have often noticed a difference too, and it's usually in lockstep with needing to adjust how I am prompting.

Put in a different way, I have to keep developing my prompting / context / writing skills at all times, ahead of the curve, before they're needed to be adjusted.

Re: Claude Sonnet 4.6

#306

Post by OtomotO »

andrewchilds wrote: post #298
grav wrote: post #278

Earlier quoted context omitted.

I fail to understand how two LLMs would be "consuming" a different amount of tokens given the same input? Does it refer to the number of output tokens? Or is it in the context of some "agentic loop" (eg Claude Code)?

I've found that Opus 4.6 is happy to read a significant amount of the codebase in preparation to do something, whereas Opus 4.5 tends to be much more efficient and targeted about pulling in relevant context.

And way faster too!

Re: Claude Sonnet 4.6

#307

Post by sumedh »

minimaxir wrote: post #112

As with Opus 4.6, using the beta 1M context window incurs a 2x input cost and 1.5x output cost when going over >200K tokens: https://platform.claude.com/docs/en/about-claude/pricing Opus 4.6 in Claude Code has been absolutely lousy with solving problems within its current context limit so if Sonnet 4.6 is able to do long-context problems (which would be roughly the same price of base Opus 4.6), then that may actually…

> Opus 4.6 in Claude Code has been absolutely lousy with solving problems

Can you share your prompts and problems?

Re: Claude Sonnet 4.6

#308

Post by alpineman »

Razengan wrote: post #186
andsoitis wrote: post #77

I’m voting with my dollars by having cancelled my ChatGPT subscription and instead subscribing to Claude. Google needs stiff competition and OpenAI isn’t the camp I’m willing to trust. Neither is Grok. I’m glad Anthropic’s work is at the forefront and they appear, at least in my estimation, to have the strongest ethics.

uhh..why? I subbed just 1 month to Claude, and then never used it again. • Can't pay with iOS In-App-Purchases • Can't Sign in with Apple on website (can on iOS but only Sign in with Google is supported on web??) • Can't remove payment info from account • Can't get support from a human • Copy-pasting text from Notes etc gets mangled • Almost months and no fixes Codex and its Mac app are a much better UX, and seem bet…

Then they can offer it cheaper as they don’t pay the ‘Apple tax’

Re: Claude Sonnet 4.6

#309

Post by michaelcampbell »

minimaxir wrote: post #215
michaelcampbell wrote: post #172

Earlier quoted context omitted.

Interesting. My CC (2.1.45) doesn't provide the 1M option at all. Huh.

Is your CC personal or tied to an Enterprise account? Per the docs: > The 1M token context window is currently in beta for organizations in usage tier 4 and organizations with custom rate limits.

The one I'm looking at right now some is sort of company level sub, so they probably have the upcharge options turned off.

Thanks!

Re: Claude Sonnet 4.6

#310

Post by comboy »

reed1234 wrote: post #284
reed1234 wrote: post #261

Earlier quoted context omitted.

not in my experience

"Opus 4.6 often thinks more deeply and more carefully revisits its reasoning before settling on an answer. This produces better results on harder problems, but can add cost and latency on simpler ones. If you’re finding that the model is overthinking on a given task, we recommend dialing effort down from its default setting (high) to medium."[1] I doubt it is a conspiracy. [1] https://www.anthropic.com/news/claude-op…

Yeah, I think the company that opens up a bit of the black box and open sources it, making it easy for people to customize it, will win many customers. People will already live within micro-ecosystems before other companies can follow.

Currently everybody is trying to use the same swiss army knife, but some use it for carving wood and some are trying to make some sushi. It seems obvious that it's gonna lead to disappointment for some.

Models are become a commodity and what they build around them seem to be the main part of the product. It needs some API.

Post reply on HN