In a few languages MAI means no/never, so it's an apt name for a Microsoft offering.
MAI-Code-1-Flash
201–210 of 297 posts
Re: MAI-Code-1-Flash
#202It'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've been doing benchmarking of various models for finding hard security bugs, and my faith in Haiku (and Sonnet, even) has dropped precipitously in the process. Self-hosted Qwen 3.6 27B consistently outperforms both for finding security bugs, which was a shocking result. I expected Qwen to be around Haiku level, maybe a little worse, and I definitely expected it to be worse than Sonnet. And, DeepSeek and MiMo perfor…
DeepSeek competes with Sonnet, not significantly worse or better. It tends to do weird things in codebases on the bigger side.
Re: MAI-Code-1-Flash
#203In a few languages MAI means no/never, so it's an apt name for a Microsoft offering.
MAI? Ma die, mai!
(gestures wildly while changing lanes in his Fiat 500)
Re: MAI-Code-1-Flash
#204Earlier quoted context omitted.
I've been doing benchmarking of various models for finding hard security bugs, and my faith in Haiku (and Sonnet, even) has dropped precipitously in the process. Self-hosted Qwen 3.6 27B consistently outperforms both for finding security bugs, which was a shocking result. I expected Qwen to be around Haiku level, maybe a little worse, and I definitely expected it to be worse than Sonnet. And, DeepSeek and MiMo perfor…
DeepSeek competes with Sonnet, not significantly worse or better. It tends to do weird things in codebases on the bigger side.
At $3/$15, Sonnet is more than an order of magnitude more expensive than DeepSeek at $0.435/$0.87 (with cached input pricing of $0.003625, DeepSeek is very good at caching, so it's very cheap to use). So, if they're equal in performance, DeepSeek is ten times better value.
But, from what I can tell DeepSeek is better than Sonnet, though I agree it is not at the level of current Opus or GPT 5.5 (but I think it probably beats Gemini Pro 3.1). I use the best model I can for code, because the cost of weaker performance is more than the $100/month I pay for Claude Opus, but it's worth knowing there are very cheap, very good, models for stuff I want to do that isn't Claude Code.
Re: MAI-Code-1-Flash
#205Curious how this handles token cost visibility.
One of the biggest pain points with AI coding tools right now
is having no idea what you're actually spending per project.
Re: MAI-Code-1-Flash
#206Where's the pelican when you need it the most?
Re: MAI-Code-1-Flash
#207It'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've been doing benchmarking of various models for finding hard security bugs, and my faith in Haiku (and Sonnet, even) has dropped precipitously in the process. Self-hosted Qwen 3.6 27B consistently outperforms both for finding security bugs, which was a shocking result. I expected Qwen to be around Haiku level, maybe a little worse, and I definitely expected it to be worse than Sonnet. And, DeepSeek and MiMo perfor…
Same opinion. Opus is best for coding, but Qwen 3.6 27b Q8 is next, before Sonnet.
Sonnet might have more knowledge and is maybe good for making excel sheets, but it does not write good code and does not follow instructions well.
But 27b Q8 needs a very beefy PC (48GB VRAM or more), so it is not an option many people can use and DS4F is so cheap right now, if you are open to externally hosted models.
Re: MAI-Code-1-Flash
#208Earlier quoted context omitted.
DeepSeek competes with Sonnet, not significantly worse or better. It tends to do weird things in codebases on the bigger side.
At $3/$15, Sonnet is more than an order of magnitude more expensive than DeepSeek at $0.435/$0.87 (with cached input pricing of $0.003625, DeepSeek is very good at caching, so it's very cheap to use). So, if they're equal in performance, DeepSeek is ten times better value. But, from what I can tell DeepSeek is better than Sonnet, though I agree it is not at the level of current Opus or GPT 5.5 (but I think it probabl…
I think there are so many variables from harnesses to tasks, making it very hard to put the models to a pecking order unless one beats another in virtually every task (like in Opus vs DeepSeek).
But all in all, I don't think we disagree.
Re: MAI-Code-1-Flash
#209The UI has Mustafa Suleyman written all over. Seems to be as much effort in rebranding MAI as in training.
Re: MAI-Code-1-Flash
#210[flagged]