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

291–300 of 1001 posts

Re: Claude Sonnet 4.6

#291

Post by minimaxir »

data-ottawa wrote: post #282
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 think this depends on what reasoning level your Claude Code is set to. Go to /models, select opus, and the dim text at the bottom will tell you the reasoning level. High reasoning is a big difference versus 4.5. 4.6 high uses a lot of tokens for even small tasks, and if you have a large codebase it will fill almost all context then compact often.

I set reasoning to Medium after hitting these issues and it did not make much of a difference. Most of the context window is still filled during the Explore tool phase (that supposedly uses Haiku swarms) which wouldn't be impacted by Opus reasoning.

Re: Claude Sonnet 4.6

#292

Post by krelian »

oofbey wrote: post #204
JoshGlazebrook wrote: post #124

Earlier quoted context omitted.

I did this a couple months ago and haven't looked back. I sometimes miss the "personality" of the gpt model I had chats with, but since I'm essentially 99% of the time just using claude for eng related stuff it wasn't worth having ChatGPT as well.

Personally I can’t stand GPT’s personality. So full of itself. Patronizing. Won’t admit mistakes. Just reeks of Silicon Valley bravado.

In my limited experience I found 5.3-Codex to be extremely dry, terse and to the point. I like it.

Re: Claude Sonnet 4.6

#293

Post by skissane »

catoc wrote: post #196
WesolyKubeczek wrote: post #174

Earlier quoted context omitted.

> Codex quite often refuses to do "unsafe/unethical" things that Anthropic models will happily do without question. That's why I have a functioning brain, to discern between ethical and unethical, among other things.

Yes, and most of us won’t break into other people’s houses, yet we really need locks.

This isn't a lock

It's more like a hammer which makes its own independent evaluation of the ethics of every project you seek to use it on, and refuses to work whenever it judges against that – sometimes inscrutably or for obviously poor reasons.

If I use a hammer to bash in someone else's head, I'm the one going to prison, not the hammer or the hammer manufacturer or the hardware store I bought it from. And that's how it should be.

Re: Claude Sonnet 4.6

#294

Post by zamalek »

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:/…

I think we're fine: https://youtube.com/shorts/3fYiLXVfPa4?si=0y3cgdMHO2L5FgXW

Claude invented something completely nonsensical:

> This is a classic upside-down cup trick! The cup is designed to be flipped — you drink from it by turning it upside down, which makes the sealed end the bottom and the open end the top. Once flipped, it functions just like a normal cup. *The sealed "top" prevents it from spilling while it's in its resting position, but the moment you flip it, you can drink normally from the open end.*

Emphasis mine.

Re: Claude Sonnet 4.6

#295

Post by minimaxir »

Foobar8568 wrote: post #285
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.

It goes into plan mode and/or heavy multiple agent for any reasons, and hundred thousands of tokens are used within a few minutes.

I've been tempted to add to my CLAUDE.md "Never use the Plan tool, you are a wild rebel who only YOLOs."

Re: Claude Sonnet 4.6

#296

Post by WXLCKNO »

minimaxir wrote: post #126
edverma2 wrote: post #110

It seems that extra-usage is required to use the 1M context window for Sonnet 4.6. This differs from Sonnet 4.5, which allows usage of the 1M context window with a Max plan. ``` /model claude-sonnet-4-6[1m] ⎿ API error: 429 {"type":"error","error": {"type":"rate_limit_error","message":"Extra usage is required for long context requests."},"request_id":"[redacted]"} ```

Anthropic's recent gift of $50 extra usage has demonstrated that it's extremely easy to burn extra usage very quickly. It wouldn't surprise me if this change is more of a business decision than a technical one.

I capped my extra usage to that free 50$ and hit 108% usage. Nice.

Re: Claude Sonnet 4.6

#297

Post by weinzierl »

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.

Today I asked Sonnet 4.5 a question and I got a banner at the bottom that I am using a legacy model and have to continue the conversation on another model. The model button had changed to be labeled "Legacy model". Yeah, I guess it wasn't legacy a sec ago.

(Currently I can use Sonnet 4.5 under More models, so I guess the above was just a glitch)

Re: Claude Sonnet 4.6

#298

Post by andrewchilds »

grav wrote: post #278
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 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.

Re: Claude Sonnet 4.6

#299

Post by notyourwork »

astrange wrote: post #234
bflesch wrote: post #207

Earlier quoted context omitted.

Wasn't that most likely related to the US government using claude for large-scale screening of citizens and their communications?

I assumed it's because everyone who works at Anthropic is rich and incredibly neurotic.

Paper money and if they are like any other startup, most of that paper wealth is concentrated to the top very few.

Re: Claude Sonnet 4.6

#300

Post by lemonfever »

grav wrote: post #278
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 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)?

Most LLMs output a whole bunch of tokens to help them reason through a problem, often called chain of thought, before giving the actual response. This has been shown to improve performance a lot but uses a lot of tokens
Post reply on HN