// 0xMech 🌙

@rachelyuqing @Teknium @VasilisStergiou 🙏 thank you!!

@Teknium @0xmech @VasilisStergiou working on it!

Kimi 2.6 looks like it could be the new contender for best open agentic model for Hermes Agent, stacking up strongly against even opus 4.6 in these agentic benchmarks 😲

@Teknium @VasilisStergiou I appreciate you 🫡

@0xmech @VasilisStergiou I hit kimi up to see if we can get this resolved..

@Teknium @VasilisStergiou

@0xmech @VasilisStergiou What was the error?

@Teknium @VasilisStergiou is there a way to use the 2.6 api with Hermes yet? tried doing it myself last night but got restricted errors due to the harness limitation

@VasilisStergiou Probably better for that then coding even tbh

@308Greenfield awesome! I used this same box for years with kodi and everything and it's 🔥 congrats

@0xmech Yup, finally broke down and ordered it.

How did I live so long without this. Goodbye crappy tv smart menu. Plex app is so much better on here. Plus direct Ethernet connection + 3GB ram.

@izzycodev @NousResearch @exolabs love your setup.. currently at the GLM 5.1 step myself.. would love to hear more about qwen and how it compares to long running, iterative tasks and coding

M4 Mac Mini + M1 Max + Qwen 3.5 35b Hermes Agent from @NousResearch running fully local with @exolabs connection between the two machines. Will report how things feel and my experience running this locally. Quickly went from Claude > GLM 5.1 > Qwen 3.5 35b Local. It's not much but it's all mine.

@0xSero do you do this yourself? if so, would you make a video on it?

Did you know you could literally transplant pieces of models into other models For example, when I'm pruning I will regularly take narrow weights, experts, or vl from one model to another You can also slice and dice things around in so many interesting ways, 8gb is good start

@jessegenet @obsdmd wow that's so impressive.. what hardware and model version are you running 5.1 locally on?!

Here is me chatting with GLM 5.1 about homeschool, its ability to recall info and plan based on the context in @obsdmd is quite solid . And yes, I need to charge my phone.

Boom, the game is changed GLM 5.1 running locally seems to actually work… Now I can run a lot of my @openclaw workflows for the cost of electricity 🔌

@theAlexFerrari @neural_avb Hermes ftw

@neural_avb I'm using this: dataimpulse.com/?aff=334221 (affiliate link I have just created from the dashboard). It's $1/GB. I am using their rotating residential proxies. You can even set how often they rotate and the countries to use. Guess who found this for me? My Hermes Agent😂

What I went with: - self-hosted searxng + firecrawl - firecrawl supports search, scrape, crawl, llm-extract - fly machines, auto-suspends on idle, cold starts in milliseconds - no proxies yet, may need it someday but that day isn't today Saving me multiple dollars every day

@astralarkitekt @Teknium how's glm treating you? looking to switch over to this model for a bit

@Teknium I just got mine up and running yesterday! Super stoked. Up and running with glm 5.1!

We made it to the NUMBER ONE spot on Github Trending!!! Thank you everyone!!

@andrewfarah going to bookmark this

sharing my first open source project a CLI for downloading and syncing your X bookmarks locally so your agent can access them. it's free › npm install -g fieldtheory › login to your X account in a chrome tab › ft sync (done!) bonus: › ft viz › ft classify

@realfrankwilder @AlexFinn concurrently? are you using these at any level for WW Frank?

@AlexFinn How are you using OpenClaw w/ Hermes?

Every AI tool you need to escape the permanent underclass: • OpenClaw • Hermes Agent • Gemma 4 running on a Mac Mini • Paperclip • ChatGPT 5.4 Pro • Claude Code • Codex app • 2nd monitor that has these agents up 24/7 Do work on 1st monitor. Constantly prompt 2nd monitor

👀 @lolwtferic just got the shout out and book deal from the man the myth the legend @BSieman on the broadcast!

@batsirai @luke_alvoeiro @FactoryAI 👀 shipping anything for that price?

@luke_alvoeiro @FactoryAI 2 missions $200 each. I’m mean…

We recently launched missions. Here's a short demo of how to get started. Excited to see what you'll build!

@RayFernando1337 @MattBroniarek did you use a preview version? or is Droid something we all can get our hands on right now?

@MattBroniarek I’m going to clone it as it was a private app for the club.

Zero humans. Forty features. Nine hours. Jensen Huang says AGI is here. I agree, and I have the screenshots to prove it. Yeah, I know. You've read this headline forty times this week. Scroll past, nobody would blame you. But I've been quietly using something since February that most people haven't caught up to yet...it's not Opus 5. The screenshots are a system that just finished a full architecture refactor of a production codebase. It found duplication I'd been living with for months and left the codebase meaningfully better than when it started. The system is Factory AI's Droid, specifically a feature called Missions. I paddle outrigger canoe in Hawaii. Our club needed an app. Not a vibe slop app...a real app. Authentication, group management, crew assignments with rotation logic so the same person isn't always stuck in seat 6, real-time chat, weather integration that warns you when wind is above 15 mph, notifications, admin controls. The kind of thing that would've cost six figures to build a few years ago. So I described what I wanted to Droid, and then I sat there watching it. It didn't just start writing code. It started asking me questions. Like, good questions. Clarifying questions about edge cases I hadn't even thought of. Then it broke the whole project into 14 milestones and 76 features. And before it wrote a single line of code, it created these things called validation contracts, basically testable assertions based on the spec so it knows what "done" actually looks like. I'm sitting there like...wait, it's planning the way I would plan? Then it started building. But here's the part that got me. When a milestone finished, separate agents came in and tested everything from the user's perspective. NOT UNIT TESTS! These agents actually opened a browser in the background and clicked through the app the way a real person would. When something failed, it didn't just retry the same thing. It went back and re-steered the entire plan. I've never seen an AI system do that successfully for many hours. I know what you're thinking, how many tokens did this cost??!? Is it burning tokens the entire time? The answer has a lot more detail than just running a Ralph loop on steroids. So I flew to San Francisco and sat with the Factory AI team to understand how this actually works under the hood. The orchestrator never writes code, it only delegates. Workers get cleared context between tasks so they don't hallucinate from stale state. And get this, the system isn't even tied to one model. You can run Claude as the orchestrator and GPT-5 as the worker. Their longest mission? Sixteen days. Can you imagine? I've been building with AI live since August 2024. I've had fifty Claude windows open (well...you know what I mean), Codex running in parallel, the whole circus. You know the feeling. This is the first time I've felt like the system was genuinely thinking through a problem the way a senior engineer would scope a project before writing a single line of code. Jensen told Lex Fridman that AGI means AI that can build a billion-dollar company. I don't know about a billion dollars, but it built my canoe club a production app while I went to make coffee. That's close enough for me.

@GDannemann boom! have a blast brother

Sometimes I get really Lucky! Can’t wait till the 4th 🩷🖤

@GDannemann any big hits?

Had a Prime time viewing these box openings! Thanks for the good time!

@GDannemann @collectdotrip English or 🇯🇵? I'm still looking to trade for dupes

@0xmech @collectdotrip I’ve opened over 20 so I have my theories 😂

TCG(m) Today marks the first expansion of The Collector Group! We are ripping @ParallelTCG live on @Pumpfun today at 12pm PST. 48 packs were up for grabs and winners have been chosen through a random drawing on our site (names posted in both discords and below the post) Come rip with us ❤️

@GDannemann @collectdotrip are you implying these boxes can be mapped good sir?

@collectdotrip Oh yeah! That is hit territory depending on which side of the box you start unless you go zigzag. So many options! Very exciting!