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

291–297 of 297 posts

Re: MAI-Code-1-Flash

#291

Post by motoboi »

chokolad wrote: post #275
motoboi wrote: post #272

To understand microsoft IA problems right now, observe that NONE of the models announced are available for use even in the microsoft foundry, which is the place were you add models to your account. I understand github copilot rollout takes time, but why can't we consume the models via microsoft own api after launching? Anthropic models are available at foundry the same moment they are launched, but not Microsoft's ow…

To understand microsoft IA problems right now observer the parent comment. It is literally false [1] but somehow creates a whole story of Microsoft inaptitude. [1] https://github.blog/changelog/2026-06-02-mai-code-1-flash-is...

Very nice. But nowhere to be seen in my model list on github copilot enterprise ai settings? I suppose it's still rolling out. The "rolling out to github copilot" is verbatim on the blog post, not my words.

On the other hand, opus 4.8 became immediately available at copilot and foundry when launched.

Mai-voice-2 and mai-transcribe are now available for me on foundry though. Just half a day after launching.

Hear me out: i love microsoft. It's sad to see this state of AI business.

Re: MAI-Code-1-Flash

#292

Post by adrian_b »

anthonypasq wrote: post #274
adrian_b wrote: post #221

Earlier quoted context omitted.

Tomorrow NVIDIA will publish Nemotron 3 Ultra, which will be the biggest open weights LLM from a US company (550B parameters). The early testers have confirmed that it is much better than all earlier US open weights models, but it is not as good as the best Chinese open weights models. While Nemotron 3 Ultra is not the smartest open weights LLM, it is well optimized for fast inference, so it is much faster than the o…

> it is well optimized for fast inference do you have any insight into the actual technical details that make this sort of things possible? I want to learn more about model architectures. Does it have to do with attention mechanisms or sparsity or something?

The model is expected to be published today on Huggingface.co, where there should be more information.

For now, this is what NVIDIA says:

  Nemotron 3 Ultra is NVIDIA's largest open model: 550B total parameters with up to 55B active per token via a hybrid Mamba-Transformer mixture-of-experts (MoE) architecture.

  Similar to Nemotron 3 Super, it was pre-trained using NVFP4 and shares the same core technical innovations:

    LatentMoE — Compresses tokens into a low-rank latent space before routing, enabling 4× as many expert specialists for the same inference cost.

    Multi-Token Prediction (MTP) — Predicts multiple future tokens in a single forward pass, improving chain-of-thought coherence and enabling built-in speculative decoding at inference time.

    1M Token Context Length — Mamba-2 layers provide linear-time complexity over sequence length, making 1M-token context practical for long-document and agentic workloads.

Re: MAI-Code-1-Flash

#293

Post by sfifs »

abustamam wrote: post #276
sfifs wrote: post #231

Earlier quoted context omitted.

Qwen is definitely the model to beat as of Mid 2026. While I didn't benchmark with SWE as my use cases are OpenClaw [1]. I found both Qwen 3.6 35B A3B and more impressively Qwen 3.5 122B A10B starting to be competitive with closed flash models. The NVFP4 quant of the latter is what I'm running now on DGX. [1] https://srinathh.medium.com/mid-size-local-models-are-now-co...

How does qwen compare to deepseek or kimi? I haven't spent much time with qwen but I find deepseek to be mostly comparable to opus for my pet projects. Kimi k2.6 did a lot of stupid stuff and talked to itself a lot "let me do X... Wait, X doesn't make sense because the user explicitly said Y" Deepseek seems to seek first to understand before going off.

Deepseek is too large for me to self host on Spark. I was actually using Deepseek as my cloud backup and it performed well but then read the T&C which doesn't give as strong data protection guarantees unlike Google and Alibaba. Kimi is again massive and cloud hosted APIs are fairly expensive compared and it also has weak T&C, so have only benched but not tested. In general I found that with OpenClaw it works better to turn Reasoning off.

I think there's possibly value to try fine tuning Qwen 3.5 on my OpenClaw turns log to see if performance improves. The one recent model I haven't tested yet is Nemotron 3 Super which I might bench soon.

Re: MAI-Code-1-Flash

#296

Post by andai »

0123456789ABCDE wrote: post #89
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.

>Is the play to plan/design/architect with a heavier model than delegate structured tasks to these smaller ones? always has been claude code has opusplan — uses opus while in plan mode, switches to sonnet for execution. https://code.claude.com/docs/en/model-config#opusplan-model-... edit: you can make it work with sonnet for planning, and haiku for execution, or any other combination you fancy to work with. https://c…

Woah, thanks. Can't believe I haven't heard of this before.

Re: MAI-Code-1-Flash

#297

Post by sfifs »

sfifs wrote: post #293
abustamam wrote: post #276

Earlier quoted context omitted.

How does qwen compare to deepseek or kimi? I haven't spent much time with qwen but I find deepseek to be mostly comparable to opus for my pet projects. Kimi k2.6 did a lot of stupid stuff and talked to itself a lot "let me do X... Wait, X doesn't make sense because the user explicitly said Y" Deepseek seems to seek first to understand before going off.

Deepseek is too large for me to self host on Spark. I was actually using Deepseek as my cloud backup and it performed well but then read the T&C which doesn't give as strong data protection guarantees unlike Google and Alibaba. Kimi is again massive and cloud hosted APIs are fairly expensive compared and it also has weak T&C, so have only benched but not tested. In general I found that with OpenClaw it works better t…

As an update, turns out Antirez created a brilliant 2 bit quant of Deepseek to fit into 128Gb systems along with a custom highlight tuned server. I've been running this the last few days and if I turn off envelope on OpenClaw, the performance is brilliant. Still to try with coding harnesses. It's a bit slow compared to the other models but so good that I'm willing to put up :-) https://github.com/antirez/ds4
Post reply on HN