News for hackers. Stuff that matters.
Re:Microsoft BitNet: 100B Param 1-Bit model for local CPUs by verdverm on Wednesday March 11, 2026 @10:35AM (#47336101)
That issue appears to be the one that's wrong. From the technical report

> We evaluated bitnet.cpp in terms of both inference speed and energy cost. Comprehensive tests were conducted on models with various parameter sizes, ranging from 125M to 100B. specific configurations for each model are detailed in the Appendix A.

Re:Microsoft BitNet: 100B Param 1-Bit model for local CPUs by webXL on Wednesday March 11, 2026 @11:34AM (#47336970)
Thanks for pointing that out. I'll ask the issue creator if they've considered that. Would be nice if the maintainer would handle that (sigh) and link to the actual models used for testing (double sigh).
Re:Microsoft BitNet: 100B Param 1-Bit model for local CPUs by verdverm on Wednesday March 11, 2026 @12:42PM (#47337905)
From what I gather, there are no models, this is a framework for running 1bit models, but none have been trained. They are mainly demonstrating the possibility.
Re:Microsoft BitNet: 100B Param 1-Bit model for local CPUs by verdverm on Wednesday March 11, 2026 @02:57PM (#47339700)
I also don't expect those with poor MCPs to have any better CLIs or APIs, most of the big companies we want them for are not investing in DX/AX. I suspect i.e. that Intuit, if they had great APIs et al, would see it as a threat to their business.

Boy would I love to give my agent access to my Quickbooks. They pushed out an incomplete MCP and haven't touched it since.

https://github.com/intuit/quickbooks-online-mcp-server