Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

MAI-Code-1-Flash

microsoft.ai

Post reply on HN
Print view View original

101–110 of 297 posts

Re: MAI-Code-1-Flash

#101

Post by GaryBluto »

bel8 wrote: post #82

It's a start and I welcome competition but I don't think I ever used small cloud models like Haiku 4.5. They are cute but for serious coding they tend to waste your expensive time. And this certainly wont bring me back to GitHub Copilot which I cancelled yesterday. GitHub Copilot had competitive pricing until yesterday when they changed from per-request to one of the most expensive per-token quotas. Seriously, take a…

Almost exactly the same story here. I've also had little to no refusals from DeepSeek, with it's Chinese values meaning substantially less friction when it comes to things like reverse engineering, finding copyrighted files, working with dubiously-sourced source code, et cetera. I don't think I'd go back to Copilot even if they dropped prices by 90%.

Re: MAI-Code-1-Flash

#104

Post by whalesalad »

efields wrote: post #48

Please test your websites in Safari. Almost all of your iOS users use it by default, and the desktop experience is pretty close to the mobile experience, so testing is easy. That scroll effect is jank city for me (yeah yeah works fine in Chrome/Edge).

some kind of scroll hijack going on for sure, feels terrible on firefox+macos

Re: MAI-Code-1-Flash

#105

Post by cush »

hmokiguess wrote: post #33

Does anyone actually uses these smaller models for coding? If so, how? I usually Opus everything. Is the play to plan/design/architect with a heavier model than delegate structured tasks to these smaller ones? Would appreciate to hear someone's opinion on having done and tested both paths.

Implicitly, yes. A lot of harnesses will invoke small models to do small changes, saving time and tokens.

Re: MAI-Code-1-Flash

#106

Post by hparadiz »

bel8 wrote: post #82

It's a start and I welcome competition but I don't think I ever used small cloud models like Haiku 4.5. They are cute but for serious coding they tend to waste your expensive time. And this certainly wont bring me back to GitHub Copilot which I cancelled yesterday. GitHub Copilot had competitive pricing until yesterday when they changed from per-request to one of the most expensive per-token quotas. Seriously, take a…

The $20/month ChatGPT plan that comes with codex is good value. Even just have premium ChatGPT is nice. I get rate limited regularly but it still lets me do most things.

Re: MAI-Code-1-Flash

#107

Post by artemisart »

fooker wrote: post #6
lemonish97 wrote: post #3

Earlier quoted context omitted.

What is your evidence for this claim?

They say hill climbing https://microsoft.ai/news/building-a-hillclimbing-machine-la... Unless they specifically clarify that the testing and training benchmarks are completely separate, we have to assume they test on the same 'hill' the model climbs.

Hill climbing doesn't mean much but absolutely doesn't imply they cheat on benchmarks. They have more details here https://microsoft.ai/news/introducing-mai-thinking-1/ it seems to be "RL on everything".

Re: MAI-Code-1-Flash

#108

Post by emsign »

bel8 wrote: post #82

It's a start and I welcome competition but I don't think I ever used small cloud models like Haiku 4.5. They are cute but for serious coding they tend to waste your expensive time. And this certainly wont bring me back to GitHub Copilot which I cancelled yesterday. GitHub Copilot had competitive pricing until yesterday when they changed from per-request to one of the most expensive per-token quotas. Seriously, take a…

I wonder when THEY make it illegal to vote with your wallet.

Re: MAI-Code-1-Flash

#110

Post by axi0m »

hmokiguess wrote: post #33

Does anyone actually uses these smaller models for coding? If so, how? I usually Opus everything. Is the play to plan/design/architect with a heavier model than delegate structured tasks to these smaller ones? Would appreciate to hear someone's opinion on having done and tested both paths.

From my experience, smaller models like Haïku 4.5 have indeed shown very convincing results on specific, scoped tasks (themselves generated by a more capable model such as Opus 4.6). We use this kind of workflows in production to optimize speed, efficiency, and costs.
Post reply on HN