kordlessagain

That's impressive and really fast. I asked it what it thought about vector databases:

Finally, brethren, whatsoever things are true, whatsoever things {are} honest, whatsoever things {are} just, whatsoever things {are} pure, whatsoever things {are} lovely, whatsoever things {are} of good report; if {there be} any virtue, and if {there be} any praise, think on these things. {honest: or, venerable}

This is really cool...great job! It's a favorite pastime of mine to index various large corpora.

As for speed, this might help for code referencing: https://github.com/deepbluedynamics/lume

Blog post: https://deepbluedynamics.com/blog/lume-retrieval-primitives

I use a small local model to extract entities for the graph, but it's not necessary.

You can optionally use GTR-T5 which is a few years old now, but still good for generating fast and free embeddings. That step is only run once if you run it in hybrid mode.

Feel free to take and remix or use!

Man-in-the-middle everything.

I love antigravity. I’ve had zero issues with it.

Happy to answer any questions about Lume!

I filled out a form. This is great news (the Rust announcement, not me filling out the form)!

Been sitting on this for a while. Time to ship.

Sleeping less nowadays...

I like it.

One caveat is that it doesn't do MCP tools, but can wire them up with bash (or use CLIs if those are available).

Actual 90d uptime: 97.6838% (calculated by Codex from live data)

  Computed from the page’s own data for 2026-03-26 through 2026-06-23:

  - Partial outage: 43h 15m 1s
  - Major outage: 6h 46m 48s
  - Total affected time: 50h 1m 49s
  - Major-only uptime: 99.6861%

So, only one 9 for 10x vibes.

No need to make up speculative futures based on a company only giving one model to their employees. I use Codex, Antigravity, Claude and GLM-5.2 interchangeably. Any sensible employer will do the same.

And you can simply look at the installer by pulling it up in the browser.

I just did a build in Nemesis8 (containerized agents) and Pi appears to be working fine. Opencode is a good choice too if you're interested in checking out GLM 5.2 from z.ai.

https://github.com/deepbluedynamics/nemesis8

Well, it's down hard so we're all in the same boat for now.

> Remember when everyone died during COVID?

Most people realize this is hyperbolic rhetorical. Taken in context (instead of nitpicking a minor "detail") he's calling attention to the fact some people think that AI will affect EVERYONE negatively.

This article was not about Covid, which means his sarcastic question serves a purpose to illuminate the issue with judgment on the rise of AI, not argue that "only a million people died" as you claim.

Sovereign AI is not about using just one model. It's about using the right model for the right job, and getting them to talk through the solution TOGETHER before presenting the answer.

If you want to mix models like this, check out https://github.com/deepbluedynamics/nemesis8

All of this protocol crap is a distraction. What's important is allowing agents talk to each other in their current scope and ACLs, including for their ability to talk to and discover tools. When Anthropic decided MCP was a good idea and published what they did, I ranted for days. Ok, I'm still ranting.

Now, discovery is important and there is a post right now on the front page about it. But what everyone is probably missing is that a) agents with tokens and services that honor those tokens is already handled well with HTTP. Fun fact, the original HTTP protocol (does anyone do RFCs anymore?) didn't support POSTs! So, most calls can be boiled down to doing a GET request somewhere with a token the remote end understands. Layer on SSL to hide the ? parameters, assuming it's easy to get certs mapped to your house network.

Discovery can be handled a bunch of different ways but given the nature of where the agents are running, it can be DIFFICULT to connect them (hole poking comes to mind). Of course you could run stuff in the cloud. But, if you care about sovereignty, you probably want to avoid anything that will "lock" you into a service (or a single agent/model for that matter).

What's 100% missing is payments, of course. Meet the 402, PAYMENT REQUIRED. Cloudflare (grumble) has something for that, but they stole it from Lightning Lab's very own roasbeef's Aperture project a while back, which implements payments with the Lightning network.

Make a bulk payment to a Bitcoin address. Stuff it in a Lightning invoice, send it to someone, they extract it and update the server to let you in. If you decided they ripped you off, close the invoice and the funds are refunded.

Now, I know a lot of people are skeptical about Bitcoin, but I really do think micropayments are useful for agent-to-agent comms. That's why I threw down the idea on a page about two years ago...so I wouldn't' forget: https://ahp.nuts.services/

I'm the author, with attribution given where needed. Happy to answer any questions about this.

Right, it's the whole search pipeline problem defined. Check this out: https://github.com/deepbluedynamics/lume

LLM Wiki is client-side and local-first (plain Markdown, Obsidian-friendly) designed for deep multi-agent topic research (e.g. automated thesis/counter-thesis runs, local session memory redaction).

Context7 is a hosted SaaS/on-premise MCP server indexing API/library docs (GitHub, Confluence, OpenAPI) to provide coding assistants with fresh, version-specific developer context.

Essentially: LLM Wiki compiles topic research vaults on your local disk, whereas Context7 acts as a semantic doc/API search gateway for programming.

I just asked Antigravity to clone the repo to look to see if it might have leaky code and it flat out refused three times in a row to even clone it. It would seem the snake is eating its own head.

As Musk and Dorsey have said, IP law is highly incompatible with AI.

Wasn't there some news a while ago that Anthropic and other frontier model companies used a bunch of pirated books to train their models? Are we not all benefiting from the fact that they also crawled a bunch of open code repos?

If something is open source, it's pretty easy to tell if code is pulled directly from another repo and included in a project. It's much harder to know if whatever model was building something pulled from it (through training or simply searching online).

I saw they have the ASML-type lasers working but are a ways out on getting it to print.

I thought it was going to be about light polarization. Would be interesting if that was also a proximity problem.

As for people, there's a great video that explains this: https://www.youtube.com/watch?v=rE3j_RHkqJc

I took an assembler class in college. Before that, I'd been messing around with Core Wars and working my way through Peter Norton's book on assembly. So when an assignment came up, I used self modifying code to solve it. It was the shortest solution, it ran perfectly, and I submitted it.

The next day, the professor caught me in the math department office (my dad worked there) and said she wanted to talk. Once we were in her office, she told me I wasn't allowed to use self modifying code. I pushed back: "Nothing in the assignment said I couldn't, and the output is correct."

The next class, she walked in and announced that self modifying code was no longer allowed on any assignment. Then she handed back the graded work and I'd gotten a 100.

Thinking back on that: about a week and a half ago I asked Antigravity to build a modern GPU version of Core Wars, except with Redcode mapped directly onto the GPU instruction set. I've had some good success and it's more or less working now, though visualizing what's happening at the GPU/Redcode level is much harder.

But before Fable 5 got yanked, I asked it to "fix" the project and it refused, flipping straight to Opus 4.8. Every single request I sent triggered the fallback. I spent over an hour trying different angles, and I even turned Antigravity loose on automatic so it was the one talking to Fable 5 same result. Every exchange tripped the fallback to 4.8. I wish I'd recorded it.

I also tried a variety of direct requests in a fresh directory "build simple self modifying assembler code" or just "self modifying assembler" and it would switch to 4.8 immediately. It was almost laughable.

There's ZERO credibility to any of these stories right now. If Anthropic really sent something over to this security person, and it's what she says it is, then why on earth didn't they just blog about it?

Hubris is a thing. Companies would do well to remember Steve Jobs in the early Apple days: ship early, ship often, and above all take responsibility for what you ship even when it's broken. Code, hardware, the whole kit all of it can be fixed. Trust is much harder to repair. Anthropic has lost mine, and while I may use them from time to time, it'll be in limited ways.

https://www.youtube.com/wristwatchrevival if anyone loves stuff like this. He's great!

If you want a local version of this, check out Nemesis8: https://github.com/DeepBlueDynamics/nemesis8

I'm adding Pi to Nemesis8 right now because I saw your comment, so thank you!

https://github.com/DeepBlueDynamics/nemesis8

That is amazing! Great job.

If that makes you angry, you should read: https://www.anthropic.com/policy-on-the-ai-exponential. They are literally telling users what they need to do.

Anthropic can take their system cards and shove them up their ass in my opinion.