Hacker News new | ask | show | jobs
by CharlesW 107 days ago
Sure, marketing people gonna market. But Haiku's 'extended thinking' mode is very different than the reasoning capabilities of Sonnet or Opus.

I would absolutely believe mar-ticles that Qwen has achieved Haiku 4.5 'extended thinking' levels of coding prowess.
1 comments
DetroitThrow 107 days ago
>Sure, marketing people gonna market.

Oh HN never change.

link
CharlesW 107 days ago
Not sure what this means, but as a marketing person myself, here's what happened: One day, an Anthropican involved in the Haiku 4.5 launch shrugged, weighed the odds of getting spanked for equating "extended thinking" with "reasoning", and then used Claude to generate copy declaring that. It's not rocket surgery!
link
DetroitThrow 107 days ago
It's mainly that people on here, regardless of profession, speak incorrectly but confidentally about things that could be easily verified with a Google search or basic familiarity with the thing in question.

Haiku 4.5 is a reasoning model, regardless of whatever hallucination you read. Being a hybrid reasoning model means that, depending on the complexity of the question and whether you explicitly enable reasoning (this is "extended thinking" in the API and other interfaces) when making a request to the LLM, it will emit reasoning tokens separately prior to the tokens used in the main response.

I love your theory that there was some mix up on their side because they were lazy and it was just some marketing dude being quirky with the technical language.

link
CharlesW 106 days ago
> It's mainly that people on here, regardless of profession, speak incorrectly but confidentally about things that could be easily verified with a Google search or basic familiarity with the thing in question.

Yep. And if your heart wants to call Haiku a "reasoning model", obviously you must listen. It doesn't meet that bar for me for a couple reasons: (1) It lacks both "adaptive thinking" and "interleaved thinking" (per Anthropic, both critical for reasoning models), and (2) it also performed unacceptably with a real-world collection of very basic reasoning tasks that I tried using it for.¹ I'm glad you're having better luck with it.

That said, it's a great and affordable little model for what it was designed for!

¹ I once made the mistake of converting a bunch of skills (which require basic reasoning) to use Haiku for Axiom (https://charleswiltgen.github.io/Axiom/). It failed miserably, and wow, did users let me have it. On the bright side, as a result I'm now far better at testing models' ability to reason.

link
throwdbaaway 107 days ago
We are all reasonable people here, and while you are (mostly) correct, I think we can all agree that Anthropic documentation sucks. If I have to infer from the doc:

* Haiku 4.5 by default doesn't think, i.e. it has a default thinking budget of 0.

* By setting a non-zero thinking budget, Haiku 4.5 can think. My guess is that Claude Code may set this differently for different tasks, e.g. thinking for Explore, no thinking for Compact.

* This hybrid thinking is different from the adaptive thinking introduced in Opus 4.6, which when enabled, can automatically adjust the thinking level based on task difficulty.

link