News for hackers. Stuff that matters.
Re:Speed up responses with fast mode by kristianp on Saturday February 07, 2026 @05:38PM (#46928933)
This is gold for Anthropic's profitability. The Claude Code addicts can double their spend to plow through tokens because they need to finish something by a deadline. OpenAI will have a similar product within a week but will only charge 3x the normal rate.

This angle might also be NVidias reason for buying Groq. People will pay a premium for faster tokens.

Re:Speed up responses with fast mode by jweir on Saturday February 07, 2026 @07:21PM (#46929882)
I switched back to 4.5 Sonnet or Opus yesterday since 4.6 was so slow and often “over thinking” or “over analyzing” the problem space. Tasks which accurately took under an minute in Sonnet 4.5 were still running after 5 minutes in 4.6 (yeah I had them race for a few tasks)

Someone of this could be system overload I suppose.

Re:Speed up responses with fast mode by stefan_ on Saturday February 07, 2026 @07:38PM (#46930007)
Yeah, nothing is sped up, their initial deployment of 4.6 is so unbearably slow they are just now offering you the opportunity to pay more for the same experience of 4.5. What's the word for that?
Re:Speed up responses with fast mode by coldtea on Saturday February 07, 2026 @08:05PM (#46930242)
Enshittification
Re:Speed up responses with fast mode by christophilus on Sunday February 08, 2026 @08:11AM (#46933897)
Enslopification.
Re:Speed up responses with fast mode by fy20 on Sunday February 08, 2026 @12:53AM (#46931675)
They mentioned in the release notes if it's over-thinking you should decrease the reasoning effort.
Re:Speed up responses with fast mode by HumanOstrich on Sunday February 08, 2026 @02:12AM (#46932019)
Edit ~/.claude/settings.json and add "effortLevel": "medium". Alternatively, you can put it in .claude/settings.json in a project if you want to try it out first.

They recommend this in the announcement[1], but the way they suggest doing it is via a bogus /effort command that doesn't exist. See [2] for full details about thinking effort. It also recommends a bogus way to change effort by using the arrow keys when selecting a model, so don't use that either.

[1]: https://www.anthropic.com/news/claude-opus-4-6

[2]: https://code.claude.com/docs/en/model-config#adjust-effort-l...

Re:Speed up responses with fast mode by SecondHandTofu on Sunday February 08, 2026 @03:50AM (#46932568)
You can do it via /model and pressing left and right though
Re:Speed up responses with fast mode by HumanOstrich on Sunday February 08, 2026 @04:41AM (#46932824)
That's not a thing, at least not in my installation of Claude Code.
Re:Speed up responses with fast mode by estsauver on Sunday February 08, 2026 @05:59AM (#46933213)
It works for me! (Edited link since original had laptops serial number in it: https://screen.studio/share/3CEvdyji)

Claude Code v2.1.37

EU region, Claude Max 20x plan

Mac -- Tahoe 26.2

Re:Speed up responses with fast mode by HumanOstrich on Sunday February 08, 2026 @08:40AM (#46934103)
Good to know it works for some people! I think it's another issue where they focus too much on MacOS and neglect Windows and Linux releases. I use WSL for Claude Code since the Windows release is far worse and currently unusable do to several neglected issues.

Hoping to see several missing features land in the Linux release soon.

I'm also feeling weak and the pull of getting a Mac is stronger. But I also really don't like the neglect around being cross-platform. It's "cross-platform" except a bunch of crap doesn't work outside MacOS. This applies to Claude Code, Claude Desktop (MacOS and Windows only - no Linux or WSL support), Claude Cowork (MacOS only). OpenAI does the same crap - the new Codex desktop app is MacOS only. And now I'm ranting.

Re:Speed up responses with fast mode by estsauver on Sunday February 08, 2026 @12:24PM (#46936428)
What version are you on? Did you run a Claude update?
Re:Speed up responses with fast mode by HumanOstrich on Sunday February 08, 2026 @12:33PM (#46936522)
I'm on v2.1.37 and I have it set to auto-update, which it does. I also tend to run `claude update` when I see a new release thread on Twitter, and usually it has already updated itself.
Re:Speed up responses with fast mode by HumanOstrich on Wednesday February 11, 2026 @01:19AM (#46971545)
Claude Code CLI 2.1.39 released a few hours ago fixes the problem. They didn't note it in the changelog though. Seems like a significant bug fix. ¯\_(ツ)_/¯
Re:Speed up responses with fast mode by saulpw on Sunday February 08, 2026 @02:42AM (#46932211)
what? Their documentation is hallucinated?
Re:Speed up responses with fast mode by HumanOstrich on Sunday February 08, 2026 @04:42AM (#46932831)
Yep, and their documentation AI assistant will egregiously hallucinate whatever it thinks you want to hear, then repeat itself in a loop when you tell it that it's wrong.
Re:Speed up responses with fast mode by oefrha on Sunday February 08, 2026 @07:30AM (#46933692)
Yesterday I asked a question about a Claude Code setting inside Claude Code, don't recall which, and their builtin documentation skill—something like that—ended up doing a web search and found a wrong answer on a third party site. Later I went to their documentation site and it was right there in the docs. Wonder why they can't bundle an AI-friendly version of their own docs (can't be more than a few hundred KBs compressed?) inside their 174MB executable.
Re:Speed up responses with fast mode by rubenflamshep on Sunday February 08, 2026 @08:15AM (#46933927)
They used to? I have a distinct memory of it doing exactly that a few months ago. Maybe it got dropped in the mad dash that passes for CC sprint cycles
Re:Speed up responses with fast mode by siva7 on Sunday February 08, 2026 @08:48AM (#46934169)
It's insane that they concluded the builtin introspection skill for claude documentation should do a web search instead of simply packing the correct documentation in local files. I had the same experience like you, wasting tokens and my time because their architecture decision doesn't work in practice.

I have to google the correct Anthropic documentation and pass that link to claude code because claude isn't able to do the same reliably in order to know how to use its own features.

Re:Speed up responses with fast mode by HumanOstrich on Sunday February 08, 2026 @08:54AM (#46934202)
Also if they bundled the documentation for the version you're running it would have fewer problems due to version differences (like stable vs latest).
Re:Speed up responses with fast mode by Der_Einzige on Sunday February 08, 2026 @07:42AM (#46933756)
Pathetic how they have no support for modifying sampling settings, or even a "logit_bias" so I can ban my claude from using the EM dash (and regular dash), semicolons, or "not". Also will upweight things like exclamation points

Clearly those whose job it is to "monitor" folks use this as their "tell" if someone AI generated something. That's why every major LLM has this particular slop profile. It's infuriating.

I wrote a long winded rant about this bullshit

https://gist.github.com/Hellisotherpeople/71ba712f9f899adcb0...

Re:Speed up responses with fast mode by nonethewiser on Saturday February 07, 2026 @10:23PM (#46931039)
"Back in my day you had to wait 3 minutes to generate 10k lines of code."
Re:Speed up responses with fast mode by neya on Sunday February 08, 2026 @12:53AM (#46931679)
Honestly, Open AI isn't worth it. I cancelled my Open AI plan (and hopefully will delete my account soon once I export all my data out) because of philosophy differences. They shared they are evaluating a model where they can get a % of your business in exchange for letting you use code generated by their AI models. That and the possible advertising angle. But, that's not even the worst, I asked ChatGPT to fairly evaluate the risky model where one for profit corporation holds your entire intimate personal details and uses it for advertising, it staunchly defended OpenAI. That was the nail in the coffin for me.

Contrast to this - Anthropic actually asks you if you want their AI to remember details about you and they have lot of toggles around privacy. I don't care if they make money from extra tokens as long as they don't go the Open AI route.

Re:Speed up responses with fast mode by prodigycorp on Sunday February 08, 2026 @06:50AM (#46933466)
> They shared they are evaluating a model where they can get a % of your business in exchange for letting you use code generated by their AI models.

That's a gross mischaracterization of what the CFO said. She basically just said the pricing space is huge, and they've even explored things like royalty models.

I'm guessing you just saw a headline and read nothing into it.

Re:Speed up responses with fast mode by hirako2000 on Sunday February 08, 2026 @08:10AM (#46933890)
Isn't it what "evaluating a model where they can get a % of your business in exchange for letting you use code generated by their AI models" precisely mean?

If they find that this business model is most profitable for OpenAI, and that they can somehow release models better than any competitor, wouldn't they say they want royalties ? That's what Unity (the game engine) does so it wouldn't be unseen.

Re:Speed up responses with fast mode by neya on Sunday February 08, 2026 @11:03PM (#46941449)
> I'm guessing you just saw a headline and read nothing into it.

https://openai.com/index/a-business-that-scales-with-the-val...

"As intelligence moves into scientific research, drug discovery, energy systems, and financial modeling, new economic models will emerge. Licensing, IP-based agreements, and outcome-based pricing will share in the value created. That is how the internet evolved. Intelligence will follow the same path."

"Intelligence will follow the same path."

This is from their official press release. Also, when you talk about "royalty models", what exactly do you think it means?

Re:Speed up responses with fast mode by nurumaik on Sunday February 08, 2026 @12:56AM (#46931698)
In cursor, GPT models already have +Fast options that work faster with 2x price
Re:Speed up responses with fast mode by tiku on Sunday February 08, 2026 @05:26AM (#46933040)
Does that just use 2 agents at the same time or something like that?
Re:Speed up responses with fast mode by jonplackett on Sunday February 08, 2026 @03:29AM (#46932461)
Gold for Anthropic but kinda shit for everyone else no? Now they have a profit motive for slowing down the normal service.

This is the Deliveroo playbook of offering a ‘premium’ service that is really just the original service with the original slowed down.

Same with speedy boarding for airlines. Now almost everyone pays for it so you don’t even get a benefit.

Re:Speed up responses with fast mode by hirako2000 on Sunday February 08, 2026 @08:14AM (#46933924)
The difference being that Airlines and food delivery did make a profit, just figured they had to do these tricks to earn some more. Mature businesses resort to lowering quality, fake scarcity.

Here the scarcity is real, and profits are nowhere to be seen

These schemes will soon fall apart entirely when an open weight model can run on Groq/Cerebras/SambaNova at even higher speeds and be just fine for all tasks. Arguably already the case, but not many know yet.

Re:Speed up responses with fast mode by Expurple on Sunday February 08, 2026 @08:20AM (#46933961)
> Now they have a profit motive for slowing down the normal service.

Sure. But for now, this is a competitive space. The competitors offer models at a decent quality*speed/price ratio and prevent Anthopic from going too far downhill.

Actually, as I think about it... I don't enjoy any other model as much as Opus 4.5 and 4.6. For me, this is no longer a competitive space. Anthropic are in full right to charge premium prices for their premium product.