I think they used a dummy model or else they would have linked to it. Just google '1-bit 100b model' and you'll only see references to this project without any download links.
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.
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).
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.
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.
Wow, that's A lot. Even though there's diminishing returns with more workers, they'd probably build them faster if they weren't scaling out so much concurrently, right?
Seems like we could match a 7 year clip at a much smaller scale. We'll be forced to at some point, but we need to overhaul the regulatory mess and fix the grid first. Hopefully that happens long before battalions of Chinese drones and droids take over the world.
Yikes, I wrote that? I hate it when people write cryptic replies like that.
What I meant was 'yes', Google Workspace CLI appears to quite similar to 'gogcli', the CLI written for OpenClaw. Both provide CLI access to a broad range of Google services for both workspace and regular gmail accounts.
GAM, on the other hand, is an admin tool, and strictly for Google Workspace accounts.
In October, I bought a $250 product from a Canadian company + about $30 shipping & taxes and thought I was good. A few weeks later, FedEx sends me an $92 bill for the duty that they had to pay. I just ignored it since I was never given that notice up front. If they really wanted it, they could have had the vendor contact me. But at least they're not getting that bit of profit now.
I'm also ignoring a bill, from UPS, that is a few bucks of duty and a much larger $14 fee. Presumably the large fee is because UPS isn't meant to collect taxes, but they can suck it.
Even if it is, it's not hard to automate PR submissions, comments and blog posts, for some ulterior purpose. Combine that with the recent advances in inference quality and speed, and probable copy-cat behavior, any panic from this theater could lead to heavy-handed crackdown by the state.
Have they found the bottom yet or are they still digging? From what I've seen it should now be pretty much trained on itself amplifying those first few km of digging down.
The journalist was almost certainly using an LLM, and a cheap one at that. The quote reads as if the model was instructed to build a quote solely using its context window.
Lying is deliberately deceiving, but yeah, to a reader, who in a effect is a trusting customer who pays with part of their attention diverted to advertising support, broadcasting a hallucination is essentially the same thing.
There are some various attempts, the problem is reliability - not that they're always up, but how do you trust them? If archive.org shows a page at a date, you presume it is true and correct. If I provide a PDF of a site at a date, you have no reason to believe I didn't modify the content before PDFing it.
