Harm Aarts

@NousResearch Is that self improvement feature the same as `RL Training (Tinker-Atropos training tools)` during the setup wizard?

Hermes Agent v0.4.0 is out:

@SoveyX How much torque can it apply? Genuinely curious.

AI is gonna take your job and your girl.

@NOOROU @Teknium What's Paperclip?

@Teknium Using it with Paperclip and GLM 5 is really enjoyable. Thanks for this great piece of software.

Hermes Agent v0.4.0 — 300 merged PRs this week. Biggest release we've done. Background self-improvement, OpenAI Responses API endpoint for your agent, new messaging platforms, new providers, MCP server management, and a lot more.

@DVATW What a drama queen. Sure, perhaps not the best decision in hindsight. But 'suicide'? Are you wanting for clicks?

This is what economic suicide looks like;

@johnrheritage @SSCryptoCurrent @heygurisingh I believe you are right. There's no 100B model released. The 'what's new' section of the repo doesn't mention it either: #whats-new" target="_blank" rel="nofollow noopener">github.com/microsoft/BitN…

@SSCryptoCurrent @heygurisingh The 4T means trained from 4 Trillion parameters - but so far they've only published up to an 8 to 10B parameter model, according to this site.

Holy shit... Microsoft open sourced an inference framework that runs a 100B parameter LLM on a single CPU. It's called BitNet. And it does what was supposed to be impossible. No GPU. No cloud. No $10K hardware setup. Just your laptop running a 100-billion parameter model at human reading speed. Here's how it works: Every other LLM stores weights in 32-bit or 16-bit floats. BitNet uses 1.58 bits. Weights are ternary just -1, 0, or +1. That's it. No floats. No expensive matrix math. Pure integer operations your CPU was already built for. The result: - 100B model runs on a single CPU at 5-7 tokens/second - 2.37x to 6.17x faster than llama.cpp on x86 - 82% lower energy consumption on x86 CPUs - 1.37x to 5.07x speedup on ARM (your MacBook) - Memory drops by 16-32x vs full-precision models The wildest part: Accuracy barely moves. BitNet b1.58 2B4T their flagship model was trained on 4 trillion tokens and benchmarks competitively against full-precision models of the same size. The quantization isn't destroying quality. It's just removing the bloat. What this actually means: - Run AI completely offline. Your data never leaves your machine - Deploy LLMs on phones, IoT devices, edge hardware - No more cloud API bills for inference - AI in regions with no reliable internet The model supports ARM and x86. Works on your MacBook, your Linux box, your Windows machine. 27.4K GitHub stars. 2.2K forks. Built by Microsoft Research. 100% Open Source. MIT License.

@johncodes Sorry if I misunderstand, but the agent need to write somewhere too right? How does persistence and agent memory work?

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - github.com/papercomputeco… * masterblaster: client utility to launch, manage, and orchestrate agents - github.com/papercomputeco… * stereosd: the stereOS system control plane daemon - github.com/papercomputeco… * agentd: the stereOS system agent management daemon - github.com/papercomputeco… Give it a try, throw us a star, and let me know what you think 🧃⭐️

Who IS this clown?

@wallstengine What interest rates are we talking about?

Coinbase $COIN is bringing back Bitcoin-backed loans for U.S. customers, excluding New York. Users can borrow against their Bitcoin without selling, marking a significant step into decentralized finance (DeFi). This time, Coinbase isn’t acting as the lender. The loans are powered by Morpho, a DeFi protocol with $3.7B in deposits. Borrowed funds are secured by converting BTC into Coinbase's cbBTC, a DeFi-compatible token. The move comes after Coinbase shut down a similar program in 2023 due to SEC scrutiny and reduced demand. Unlike previous crypto lending platforms that collapsed during the 2022 crypto winter, Coinbase says this program ensures user custody and leverages DeFi principles like overcollateralization to manage risks. While users gain access to DeFi lending without the complexity, they still bear the risks of liquidation and variable interest rates. With billions in BTC on Coinbase, this could inject significant liquidity into the DeFi ecosystem.

I've been trying to coax my Sonos speakers to play something, anything, the last 30 minutes. I'm glad New Glenn launched successfully, otherwise I'd be very annoyed

@BobMcElrath El Salvador yielded to the demands of the IMF. They wanted the loan more than they wanted their Bitcoin economy.

@haarts IMF loans can be extremely predatory, and countries don't usually have another option. Bitcoin is a new bargaining chip.

OTOH, this is a demonstration of a new kind of leverage small countries have over the IMF. Others will follow.

Gaan ze ons ook vertellen wat die #grenscontroles opgeleverd hebben? Nee? Verrassend.

@fsiefken Imagine the people fooled by that theatre... But you are probably right on the first count

Imagine being one (or a bunch) of the most powerful people on the planet and eating this crap.

@lakegoneforever @COLDCARDwallet @nvk @bitkey @jack Bitbox2

@mdradvies Lekker

Het zou echt hi-la-risch zijn als er alleen maar vegan halal shit besteld was...

Nogmaals mensen, niet dit soort filmpjes delen waar Geert Wilders door de mand valt. Het zou hem zo maar weer 5 zetels kunnen gaan kosten. Dat willen we toch niet? #WegMetWilders

Finally! Now NASA need to come up with a space program. Not a job program.

@elonmusk They are pricing in externalities. As one should

Wow, electricity prices are crazy high in the UK and Europe!