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

61–70 of 297 posts

Re: MAI-Code-1-Flash

#61

Post by linuxhansl »

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.

I am using Opus 4.x at work, and these "smaller" (20-80bn, 3-4bn active) models at home. Unfortunately there is no comparison, yet (IMHO anyway).

With Opus I can work, trust its designs, architecture suggestions, and code changes, even in a complex code base.

The smaller models seem to "try". They work for smaller tasks, but for more complex task it's often more work than doing it myself.

I wish it were different, and maybe in a year or two it will be.

Re: MAI-Code-1-Flash

#62

Post by minraws »

giancarlostoro wrote: post #57
camelmel wrote: post #43

Huh, according to that model card this is a 137B total parameter model. Performance doesn't seem that good: - MAI-Code-1-Flash (137B-A5B) = 51% on SWE-bench pro - Qwen3.6-35B-A3B = 49.5% on SWE-bench pro ( https://huggingface.co/Qwen/Qwen3.6-35B-A3B ) They benchmark against Claude Haiku but Haiku is not good, it's worse than tiny open models you can run locally or via API at 10% the cost.

The take away is that this model is a smaller model that competes with Haiku, I would hope they come out with a "Sonnet" competing model, then Opus. I have been wondering why Microsoft is kind of "sleeping" on offering models they themselves have made on Copilot, maybe it was part of their deal with OpenAI? Not sure.

They did release, MAI-Thinking-1 to compete with Sonnet. Totally not sure why that isn't at the top here.

Re: MAI-Code-1-Flash

#63

Post by hmokiguess »

dist-epoch wrote: post #46
hmokiguess wrote: post #42

Earlier quoted context omitted.

Do you mind sharing your workflow? What do you mean by fraction of the money, in my case personally, I'm yet to reach a session limit on the subscription plan. I'm not "tokenmaxxing" as they say, so hard to see a scenario in which the plan is expensive for the value I get.

If you don't hit a limit running Opus, it means you are very much in the loop. For example you probably don't have days where you ask Opus to review your whole code base and look for code duplication/technical debt/robustness issues, and then to fix some of the found issues, and do this 3-5 times until no big issues are found anymore.

What’s your prompt for this, the way you described it made it seem like there’s a generalizable way I can go about this. I just rely on a testing pipeline instead so can’t think of why I would need to proactively find holes where tests haven’t already done that for me.

Re: MAI-Code-1-Flash

#65

Post by wetpaws »

camelmel wrote: post #43

Huh, according to that model card this is a 137B total parameter model. Performance doesn't seem that good: - MAI-Code-1-Flash (137B-A5B) = 51% on SWE-bench pro - Qwen3.6-35B-A3B = 49.5% on SWE-bench pro ( https://huggingface.co/Qwen/Qwen3.6-35B-A3B ) They benchmark against Claude Haiku but Haiku is not good, it's worse than tiny open models you can run locally or via API at 10% the cost.

[dead]

Re: MAI-Code-1-Flash

#66

Post by giancarlostoro »

minraws wrote: post #62
giancarlostoro wrote: post #57

Earlier quoted context omitted.

The take away is that this model is a smaller model that competes with Haiku, I would hope they come out with a "Sonnet" competing model, then Opus. I have been wondering why Microsoft is kind of "sleeping" on offering models they themselves have made on Copilot, maybe it was part of their deal with OpenAI? Not sure.

They did release, MAI-Thinking-1 to compete with Sonnet. Totally not sure why that isn't at the top here.

Good question, and I missed that entirely!

Re: MAI-Code-1-Flash

#68

Post by necubi »

redrove wrote: post #27
capten wrote: post #10

It's so weird to me that the benchmarks remain so low, but the models are marketed as revolutionary. And if you say that low coding capabilities aren't a problem, say that to the token price hike and 'general use' model setup. Why not sell it as a math agent? Why do I have to set up 4 agents to check each others' work?

It’s about bang for buck. That high a score for 5B params is pretty good, nigh unbelievable a short while ago. It is my belief that smaller models will get better and better, and even cloud SOTA models will shrink. Yet another reason the current buildout will feel like the railroads.

It's 5B active params in MoE, not 5B total params (total is 137B).

Re: MAI-Code-1-Flash

#69

Post by giancarlostoro »

Mark Zuckerberg must be in crisis. Microsoft releasing models that compete with Claude's models. Meanwhile the only thing anyone knows about Mark's models is that they help you get hacked more easily.
Post reply on HN