Mino 2.5 has been my workhorse for coder and tester agents (the ones planner agents delegate tasks to)
Xiaomi Mimo 2.6 live post-training dashboard
51–60 of 146 posts
Re: Xiaomi Mimo 2.6 live post-training dashboard
#52[dead]
Re: Xiaomi Mimo 2.6 live post-training dashboard
#53I been using MiMo-V2.5 to do most of my work as software engineer, on a variety of projects I'm working on, and I been VERY happy with ROI. The model is very powerful! Not perfect – I've run in hallucination loops once or twice, but nothing a stop-then-continue wouldn't solve. The cost is unbelievably low, and the quality of intelligence I get is equivalent to when I was working mostly with Anthropic models (late las…
May I ask why you ended up there instead of just using the heavy subsidized subscription. I’m actually curious.
Mimo has subsidized subscriptions too
Re: Xiaomi Mimo 2.6 live post-training dashboard
#54I been using MiMo-V2.5 to do most of my work as software engineer, on a variety of projects I'm working on, and I been VERY happy with ROI. The model is very powerful! Not perfect – I've run in hallucination loops once or twice, but nothing a stop-then-continue wouldn't solve. The cost is unbelievably low, and the quality of intelligence I get is equivalent to when I was working mostly with Anthropic models (late las…
I am also using 2.5 and it is giving me solid results. Its available free on Openrouter
Re: Xiaomi Mimo 2.6 live post-training dashboard
#55Distillation in real-time? Very interesting!
Re: Xiaomi Mimo 2.6 live post-training dashboard
#56I been using MiMo-V2.5 to do most of my work as software engineer, on a variety of projects I'm working on, and I been VERY happy with ROI. The model is very powerful! Not perfect – I've run in hallucination loops once or twice, but nothing a stop-then-continue wouldn't solve. The cost is unbelievably low, and the quality of intelligence I get is equivalent to when I was working mostly with Anthropic models (late las…
How does it compare with DS 4.1 Flash in your experience, if you ignore the cost?
Re: Xiaomi Mimo 2.6 live post-training dashboard
#57I been using MiMo-V2.5 to do most of my work as software engineer, on a variety of projects I'm working on, and I been VERY happy with ROI. The model is very powerful! Not perfect – I've run in hallucination loops once or twice, but nothing a stop-then-continue wouldn't solve. The cost is unbelievably low, and the quality of intelligence I get is equivalent to when I was working mostly with Anthropic models (late las…
[flagged]
Re: Xiaomi Mimo 2.6 live post-training dashboard
#58Well, if open source AI is dangerous (for OpenAI/Anthropic IPOs?), this is like watching a time bomb.
the open burial started when zAI served their latest model on all Chinese chips.
now we r just noticing the grave getting dug deeper.
Re: Xiaomi Mimo 2.6 live post-training dashboard
#59I been using MiMo-V2.5 to do most of my work as software engineer, on a variety of projects I'm working on, and I been VERY happy with ROI. The model is very powerful! Not perfect – I've run in hallucination loops once or twice, but nothing a stop-then-continue wouldn't solve. The cost is unbelievably low, and the quality of intelligence I get is equivalent to when I was working mostly with Anthropic models (late las…
[flagged]
Real?
Re: Xiaomi Mimo 2.6 live post-training dashboard
#60You'd think they would make it less obvious that they are running their whole operation with Claude
They'd be running in the red then cause they charge way less than Claude. Sorry but it just doesn't make logical sense. They have open source, papers, and self hosting too