MiMo Code is now released and open-source
151–160 of 338 posts
Re: MiMo Code is now released and open-source
#152Earlier quoted context omitted.
Frankly, it's not really more insecure than any other installation method. Apt packages and the like generally have the ability to specify pre/post-install scripts, so `sudo dpkg -i ./random.deb` is equivalent to `sudo bash ./random.sh`. Even if they didn't have pre/post-install scripts, they're still writing arbitrary files to arbitrary locations on your disk, so they can trigger execution the next time you boot or…
A package (like a .deb) is a static artifact. It can be hashed, mirrored, and GPG-signed. Package managers usually verify that signature before any pre/post-install scripts. A "curl | bash" pipe is a dynamic stream; the server can perform targeted attacks: sending a clean script to 99% of users and a malicious payload only to a specific IP address or User-Agent. This allows for targeted attacks that are invisible to…
Like requiring a WoT (usually with physical meetups) vetting people creating packages, FTP-masters, dedicated clean buildbots, etc. in addition to the packages themselves being signed and so on.
Re: MiMo Code is now released and open-source
#153Re: MiMo Code is now released and open-source
#154It's interesting that it renders Chinese in a TUI. I wonder if that breaks anything that assumes a character is always a column wide.
Re: MiMo Code is now released and open-source
#155What a transformation by Xiaomi to build almost frontier level models. Five years back, when I was in the data science team, they dint really bother about AI models and were using Baidu for NLP and vision under the hood of their APIs
Wrote this eons ago: I fully expect Baidu and other tech giants on the Chinese shores to try and push the boundaries of technology. Silicon Valley (and the US) in general has always been the hot-bed of innovation. But with enormous increase in wealth in China (and to an extent in India), I can see these companies being more and more ambitious. Not long ago Andrew Ng of Coursera and Stanford AI Lab fame joined Baidu t…
Re: MiMo Code is now released and open-source
#156Claude and Codex pricing will eventually have to come down, for most common coding tasks you don't need a super smart slow model but a smart-enough and very fast one.
Re: MiMo Code is now released and open-source
#157As much as I absolutely love Mimo V2.5 Pro (it's a genuinely good model), I absolutely hate the way they calculate usage in their token plan. For example: For a super small task in a small project that should not be consuming more than 500K total tokens after all tool calls included, their shown usage shot up to 152 million tokens. But, when I scroll down on the same page, a table shows usage as 3 million tokens, out…
Re: MiMo Code is now released and open-source
#158Good, coding harnesses should be open source and LLMs should be treated as commodities. Minimize switching costs for consumers, and let people understand how they're interacting with the context and the LLM outputs. The industry has been moving the wrong direction with Claude Code staying closed (despite multiple times leaking the source code!) and the open source Gemini CLI being deprecated in favor of closed source…
Why would a company do any of these things? What is their motivation for any of it? That’s like saying cloud providers should be commodity and should open source all of their platforms and eliminate egress fees so customers can easily leave at any point in time. That’s a charity, not a business model.
Re: MiMo Code is now released and open-source
#159What a transformation by Xiaomi to build almost frontier level models. Five years back, when I was in the data science team, they dint really bother about AI models and were using Baidu for NLP and vision under the hood of their APIs
https://en.wikipedia.org/wiki/Xiaomi_Mi_1
And now they make one of the fastest cars ever created and frontier-level AI. In just over a decade. 你好!
Re: MiMo Code is now released and open-source
#160As much as I absolutely love Mimo V2.5 Pro (it's a genuinely good model), I absolutely hate the way they calculate usage in their token plan. For example: For a super small task in a small project that should not be consuming more than 500K total tokens after all tool calls included, their shown usage shot up to 152 million tokens. But, when I scroll down on the same page, a table shows usage as 3 million tokens, out…
It's very confusing. They have tokens for their API and credits for their "token plan".
"""
Credits 4,100,000,000 Credits
Total Token Consumption
"""