Pinned Tweet
I'm settling into a three-agent pattern lately:
- life agent : Muse
- homelab agent: Hermes
- coding agent: codex
I know how to do all of this with a single agent like Hermes. But the user experience for the other two is actually keeping me in them for these domains
halr9000 retweeted
Genie 4 is quite an insane experience, generating game-like enviornments as you go. It isn't flawless but I can type "Neogothic brutalist city inhabited by robots and horses" & it creates one in a minute. Then I asked it to add dragons. Then a friendly otter NPC. All in realtime
Who doesn't like a well-curated awesome list?! Here's a cool one if you've not seen it yet on harness engineering.
I feel smarter just skimming the TOC. 😁
github.com/ai-boost/awesome-…
halr9000 retweeted
🌍 WanGP v18.81 — The One World Generator
Build a world from text with Hy-Nomas or from an image with EVOKE, then explore it with your keyboard! Save your progress, record your journey and revisit familiar places—starting at 8 GB VRAM thanks to MMGP v4.
🤖 Deepy Prime your local Agent gets roughly 2× the context at the same VRAM, plus new abilities:
🔎 Search the web and find compatible LoRAs
🐍 Create graphics, animations and batch workflows with Python
🧊 Generate 3D assets and explorable worlds
🎬 Restore, upscale and outpaint videos through Media Flow
Free to run locally. Your GPU has more places to take you.
github.com/deepbeepmeep/WanG…
halr9000 retweeted
If you've ever wondered why smart TVs are so cheap, this is why.
@log4j rooted his Samsung and found an always-on hot mic, automatic content recognition, geolocation, network mapping, ad targeting and user profiling, shared with Samsung's "400 partners".
A lot of it can be blocked in <15 min, wrote a basic guide below.
What your TV is doing
The main culprit is ACR (automatic content recognition). Your TV screenshots what's on screen, fingerprints it, and sends it home to build your ad profile. Samsung does it every 500ms, LG every 10ms [1].
What is insane: it happens on connected devices too.
Plug in your laptop, your console, your work machine, and your TV can fingerprint that via HDMI [1].
He also found that if your Samsung doesn't have a mic, it'll look for one from a connected soundbar or bluetooth device.
teapawt.net/log4j/status/211376224…
It's on by default, and you likely agreed to it on the setup screen you clicked through in 10 seconds.
Step 1: Turn off ACR
Samsung: Terms & Privacy → Viewing Information Services
LG: Live Plus
Vizio: Viewing Data
Roku: "Use info from TV inputs"
Sony/Google TV: Samba Interactive TV
Menus vary by model, but those are the names to look for. While you're in there, opt out of interest-based ads, reset your advertising ID, decline every optional privacy agreement, turn off voice recognition, and delete apps you never open.
Step 2: Give smart devices their own network
Put the TV, cameras, speakers and vacuum on your router's guest/IoT network. The logic is simple: these devices rarely get patched. If one gets compromised (getting drastically more frequent with AI), it shouldn't be able to see your other devices or home network.
Step 3: Block trackers for the whole house with DNS-level filtering
NextDNS (cloud-based) is easy and has a solid free plan. Pi-hole is a little bit more work if you prefer self hosting. For simplicity we'll focus on the former.
1. Sign up at nextdns.io (free tier is plenty)
2. Privacy tab: add a blocklist (OISD is a good bet) and turn on Native Tracking Protection for Samsung, LG, Roku, Amazon (see attached image)
3. Setup tab: copy your endpoint
4. Paste it into your router's DNS settings as DNS-over-HTTPS/TLS (or use the IPs + "Link IP" if your router only does plain DNS)
5. Bonus: block outbound port 53 except to your router. Some devices hardcode their own DNS to get around you
Then open the NextDNS logs and watch how often your TV phones home. It's eye-opening. If an app or update breaks, find the domain in the logs and allowlist it.
Why they do this
TV prices are down 97% since 2000 [2]. Most of that is better manufacturing and brutal competition. But once margins on the hardware hit zero, the cost moved to you.
In Q3 2024, Vizio lost $6.7M selling TVs and made $115.8M in gross profit from ads and viewing data [3]. They've said on earnings calls that they keep TV prices low to grow the audience they sell to advertisers. Walmart bought them in 2024.
This isn't a conspiracy theory either. Vizio paid $2.2M to the FTC in 2017 for tracking 11 million TVs without consent. Last December, Texas sued Samsung, LG, Sony, Hisense and TCL over ACR. Samsung and LG have since agreed to stop collecting that data without explicit consent [4].
TL;DR
1. ACR off
2. Ads + voice off
3. Smart devices on their own network
4. NextDNS filtering on the router
Sources:
[1] ACR study: arxiv.org/abs/2409.06203
[2] Cost of US consumer goods: aei.org/economics/chart-of-t…
[3] Vizio Q3 2024: sec.gov/Archives/edgar/data/…
[4] Texas v. Samsung: texasattorneygeneral.gov/new…
I just had to stop myself and delete a two sentence thank you note to my agent.
In my defense, the model was very thoughtful.
That's a strong message and I like it
Do you know the meaning of the @NousResearch logo?
The girl is called the "Nous Girl". She was drawn in July 2023 by Nous's first artist, who goes by John Galt. Yes, the Atlas Shrugged rebel
She stands for the rebellion of decentralized AI, and for keeping our humanity in the face of censorship and machine intelligence
The words around her: "Rebellion to tyrants is obedience to God."
That line goes back to 1776. Jefferson, Franklin and Adams put it on their proposed Great Seal of the United States. Congress said no, so Jefferson put it on his own personal seal instead
Nous pointed it at AI. Today's tyrants are closed labs and gatekeepers deciding who gets access to intelligence. The rebellion is open weights, open agents and open infrastructure.
That's why I build on Hermes
Wearing it proudly 🏴
halr9000 retweeted
Maestro v3.0 is out! Huge focus on H3 speed across GPUs, + Flux3 & other goodies!
Two weeks! That’s how long it’s been since I pushed an update. The longest since launch. Been grinding!
Maestro: Free, Local, Easy, Open
70k+ installs in 3 months!
More in 🧵
It’s SO FAST!👇
halr9000 retweeted
🚀 WanGP v18 — Distortion of Space and Time!
🧊 Go 3D: turn images and videos into 3D assets and scenes. Explore them in the new 3D Viewer.
🎨 Full creative coverage: image, video, audio and now 3D—all in one app.
⚡ More speed: VAEs up to 3.5× faster, H3 generation up to 2× faster with Veda Sparse.
🆕 New models: Kandinsky 6.0, Wan 2.2 Prism, Hunyuan3D 2.1, TRELLIS.2 and more
🤖 Made for agents: expanded MCP tools to create, inspect and organize media. Let your agent handle the workflow.
💾 Built for the GPU poor. Free to run locally.
github.com/deepbeepmeep/WanG…
Just one of countless examples why open source is vital fuel for innovation.
We were able to fine tune an open weight model (Qwen3.5-9B) on proprietary internal data at @coinbase, and it out performed frontier models, at much lower cost and speed, for a specialized task (fraud prevention in this case).
I think we'll see more of this pattern inside companies. The frontier models are amazing generalists. But increasingly you'll see specialist models out perform on more narrow tasks, either working on teams, or by themselves.
We're making it easy to fine tune models internally for our employees. We even have a skill for it in our internal harness that makes it easy to spin these up and start training them:
"/fine-tune-and-serve-llm I want to fine-tune Qwen for payments risk review. help me get started"
I imagine we'll have some backend services that could be replaced entirely by this new architecture.
This is amazing and excellent and it makes me happy.
Introducing Anatomy
Describe a machine in one line. Claude brings it to life.
- Interactive isometric wireframes you can rotate, inspect and explore
- WebGL shaders for fire, water, plasma and more
- Real 3D motion, with individual parts that rotate and move
Install it as an agent skill. Fully open source.
I don't mind at all doing the complicated stuff for my home lab. But that's hobby. When it's time to pay the bills, I need things to just work.
For example, it's a major pain to set up Google authentication for an individual using an open source project. Doable, but there's just a lot of steps involved. It's one step for Muse (and several others with corporate backing). Repeat that across multiple saas providers
It's still ok to say "my bot", right? Sometimes me and my bots are just chillin' and I need to be able express myself freely without going all, "mY aGeNt" all the time.
I feel like this is an appropriate appropriation, for me. :D Checking out github.com/androoAGI/starnet now. Looks pretty cool way to run an agent.
