News for hackers. Stuff that matters.
Re:Claude Haiku 5.5 by patrickwdaly on Wednesday October 07, 2026 @02:12PM (#49996610)
How are y'all using Haiku though? I rarely select it.
Re:Claude Haiku 5.5 by mariocesar on Wednesday October 07, 2026 @02:18PM (#49996711)
I have a zsh functions that calls claude code with haiku to suggest commit messages, is faster and the instructions are two lines.

I also have an "ask" script that I use daily to ask simple stuff, it can access websearch and webfetch, it's more than enough to parse logs, ask for commands, quick research on the internet, small stuff. https://github.com/mariocesar/dotfiles/blob/main/common/.loc...

I use haiku for things that needs to be quick, have really clear instructions.

Re:Claude Haiku 5.5 by tetraodonpuffer on Wednesday October 07, 2026 @04:44PM (#49998555)
with claude -p seemingly now using api credits I guess this approach will have to change unfortunately :/ I wonder what will be the best cmdline way to do things like these
Re:Claude Haiku 5.5 by swalsh on Wednesday October 07, 2026 @02:21PM (#49996749)
I've been using GPT-6 Luna in some capacity for nearly all my agent workflows. It's just a really good model, and the pricing is cheap. If Haiku 5.5 is better, and the same price (under 100k context... which is a big caveat) i'd probably swap it.
Re:Claude Haiku 5.5 by dannyw on Wednesday October 07, 2026 @02:25PM (#49996829)
It’s absolutely better than Luna. It feels closer to a “sonnet 5.2” if that makes sense.

Of course it’s not as big, and hence falls-off quicker. I’d consider the 100k a “promotional price” to match Luna’s token pricing while delivering noticeably more intelligence.

Re:Claude Haiku 5.5 by svachalek on Wednesday October 07, 2026 @02:15PM (#49996651)
Opus often picks it when it's doing a "find me something" subagent. But largely it's been held back by being fully a year old at this point, and priced at a much higher price than models that are far more capable.
Re:Claude Haiku 5.5 by notatoad on Wednesday October 07, 2026 @02:49PM (#49997155)
not haiku, but luna - last week i used it for things like "read this historical dump of 15k support tickets and break them into categories that make sense, then propose help docs that i could write to handle the most frequent queries in each category"

used <10% of my 5hr limit on a $100 codex plan.

Re:Claude Haiku 5.5 by hector_vasquez on Wednesday October 07, 2026 @03:14PM (#49997460)
My software application uses Haiku in production more or less as a Jev. I do not use it for coding or development.
Re:Claude Haiku 5.5 by mrkn1 on Wednesday October 07, 2026 @04:33PM (#49998438)
Why not have a CPU-first decision model for free? check out gutsy
Re:Claude Haiku 5.5 by gghootch on Wednesday October 07, 2026 @02:21PM (#49996747)
I was waiting for this.

Planning on doing flash analyses of PRs that impact evals in some way, and then post comments on GitHub whenever there’s flaws in them

( https://evalship.com )

Re:Claude Haiku 5.5 by steve_adams_86 on Wednesday October 07, 2026 @02:16PM (#49996658)
It's great at parsing documents inexpensively. For the few skills/plugins I've made, I usually instruct Claude to use Haiku for low-reasoning grunt work.
Re:Claude Haiku 5.5 by Plutoberth on Wednesday October 07, 2026 @02:33PM (#49996938)
I'm building a game that incorporates LLMs as a game mechanic.

I've been using Luna, but I'll probably switch to Haiku.

Re:Claude Haiku 5.5 by apothegm on Wednesday October 07, 2026 @09:03PM (#50000799)
Translating GPT’s word salad to English at the end of an agent interaction.