Ditto. I've found it pretty tolerable once I've used "ShutUp10!" to disable the annoying stuff. I've used harder tools than it, but I've then found it breaks useful stuff (like the Xbox Gaming stuff, which some MSFT games use).
> Claude Haiku 4.5, a new hybrid reasoning large language model from Anthropic in our small, fast model class.
> As with each model released by Anthropic beginning with Claude Sonnet 3.7, Claude Haiku 4.5 is a hybrid reasoning model. This means that by default the model will answer a query rapidly, but users have the option to toggle on “extended thinking mode”, where the model will spend more time considering its response before it answers. Note that our previous model in the Haiku small-model class, Claude Haiku 3.5, did not have an extended thinking mode.
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!
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.
> 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.
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.
I thought there would be one or two results, perhaps a result of poor reoccurring phrasing. Nope.
>i'm going to change your diaper and burp you
>Carlito is a very good boy Go piss in your diaper you big baby
>He doesn't care. He is a big baby who filled up his diaper with pee pee and poo poo
>you are a big baby and i am going to change your diaper and burp you <
>To be clear I call executives of multi trillion dollar companies scumbags and if you can't deal with that I'm not sure what to do. Burp you? Change your diaper?
>I am going to change your diaper and burp you
>Yeah man it's real authoritarian to say your second name is doodoo. Go change your diaper you big baby
>Yeah because you're a big baby with a big full diaper
>Hello sir this is your uber outside. I have your order from the diaper store
I find Zitron's writing bad and his character questionable but exaggerated accusations like this is why no one takes sexual assault accusations from progressives seriously any more.
You guys spent a decade crying wolf about how everything is literally sexual assault and now you wonder why conservatives are being so successful cracking down on sexual deviance using fabricated accusations. You reap what you sow.
You're reading your own hangups and bugaboos into my comment. The problem begins and ends with the lack of consent. There are plenty of people who would be into it if he asked first.
This is it - you’ve got to be deliberate in scrolling immediately past anything remotely thirst-trappy, otherwise the algorithm hyperfixates. And then overstay your welcome at the type of content you want to see.
In my experience, it has worked (my discover page is an amalgamation of classic Simpsons, Dropout.tv, and Whose Line Is It Anyway?, while my Reels feed is unhinged in the right way.) But also I’ve stopped using it because my brain was melting.
reply