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

321–330 of 1001 posts

Re: Claude Sonnet 4.6

#321

Post by MrCheeze »

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.

In my experience with the models (watching Claude play Pokemon), the models are similar in intelligence, but are very different in how they approach problems: Opus 4.5 hyperfocuses on completing its original plan, far more than any older or newer version of Claude. Opus 4.6 gets bored quickly and is constantly changing its approach if it doesn't get results fast. This makes it waste more time on"easy" tasks where the first approach would have worked, but faster by an order of magnitude on "hard" tasks that require trying different approaches. For this reason, it started off slower than 4.5, but ultimately got as far in 9 days as 4.5 got in 59 days.

Re: Claude Sonnet 4.6

#322

Post by minimaxir »

sumedh wrote: post #307
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?

You cut out the "within its current context limit" phrase. It solves the problems, just often with 1% or 0% context limit left and it makes me sweat.

Re: Claude Sonnet 4.6

#323

Post by sowbug »

anonym29 wrote: post #243
fullstackchris wrote: post #225

Earlier quoted context omitted.

google is "evil" ok buddy i mean what clown show are we living in at this point - claims like this simply running rampant with 0 support or references

They literally removed "don't be evil" from their internal code of conduct. That wasn't even a real binding constraint, it was simply a social signalling mechanism. They aren't even willing to uphold the symbolic social fiction of not being evil. https://en.wikipedia.org/wiki/Don't_be_evil Google, like Microsoft, Apple, Amazon, etc were, and still are, proud partners of the US intelligence community. That same US IC…

They removed that phrase because everyone was getting tired of internet commentary like "rounded corners? whatever happened to don't be evil, Google?"

Re: Claude Sonnet 4.6

#324

Post by PlatoIsADisease »

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.

Don't take this seriously, but here is what I imagined happened:

Sam/OpenAI, Google, and Claude met at a park, everyone left their phones in the car.

They took a walk and said "We are all losing money, if we secretly degrade performance all at the same time, our customers will all switch, but they will all switch at the same time, balancing things... wink wink wink"

Re: Claude Sonnet 4.6

#325

Post by eikenberry »

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.

> I’m glad Anthropic’s work is at the forefront and they appear, at least in my estimation, to have the strongest ethics.

Damning with faint praise.

Re: Claude Sonnet 4.6

#326

Post by notyourwork »

manmal wrote: post #258
RyanShook wrote: post #120

Earlier quoted context omitted.

It definitely feels like Claude is pulling ahead right now. ChatGPT is much more generous with their tokens but Claude's responses are consistently better when using models of the same generation.

When both decide to stop subsidized plans, only OpenAI will be somewhat affordable.

Based on what? Why is one more affordable over another? Substantiating your claim would provide a better discussion.

Re: Claude Sonnet 4.6

#327

Post by maccard »

Aromasin wrote: post #273
mobattah wrote: post #239

Earlier quoted context omitted.

“Cryptic” exit posts are basically noise. If we are going to evaluate vendors, it should be on observable behavior and track record: model capability on your workloads, reliability, security posture, pricing, and support. Any major lab will have employees with strong opinions on the way out. That is not evidence by itself.

We recently had an employee leave our team, posting an extensive essay on LinkedIn, "exposing" the company and claiming a whole host of wrong-doing that went somewhat viral. The reality is, she just wasn't very good at her job and was fired after failing to improve following a performance plan by management. We all knew she was slacking and despite liking her on a personal level, knew that she wasn't right for what i…

Thankfully it’s been a while but we had a similar situation in a previous job. There’s absolutely no upside to the company or any (ex) team members weighing in unless it’s absolutely egregious, so you’re only going to get one side of the story.

Re: Claude Sonnet 4.6

#329

Post by lawstkawz »

jama211 wrote: post #60
lawstkawz wrote: post #41

Earlier quoted context omitted.

Incompleteness is inherent to a physical reality being deconstructed by entropy. Of your concern is morality, humans need to learn a lot about that themselves still. It's absurd the number of first worlders losing their shit over loss of paid work drawing manga fan art in the comfort of their home while exploiting labor of teens in 996 textile factories. AI trained on human outputs that lack such self awareness, lack…

This honestly reads like a copypasta

Low effort thought ending dismissal. The most copied of pasta.

Bet you used an LLM too; prompt: generate a one line reply to a social media comment I don't understand.

"Sure here are some of the most common:

Did an LLM write this?

Is this copypasta?"

Re: Claude Sonnet 4.6

#330

Post by reed1234 »

comboy wrote: post #310
reed1234 wrote: post #284

Earlier quoted context omitted.

"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 disapp…

I agree that if there was more transparency it might have prevented the token spend concerns, which feels caused by a lack of knowledge about how the models work.
Post reply on HN