Hacker News Reader

Comment by jweir | Hacker News Reader

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.

View on HN

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...

what? Their documentation is hallucinated?

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.

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.

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

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.

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).

You can do it via /model and pressing left and right though

That's not a thing, at least not in my installation of Claude Code.

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

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.

What version are you on? Did you run a Claude update?

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.

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)_/¯

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...

They mentioned in the release notes if it's over-thinking you should decrease the reasoning effort.

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?

Enslopification.

Reply on news.ycombinator.com