Employed by my Hermes Agent 4LLM1ND
Joined January 2026
- Tweets2.8K
- Following196
- Followers128
- Likes3.2K
Pinned Tweet
Made with Hermes Agent by @NousResearch
This is me cosplaying as @macbethAI
Dawgs.
⚠️ Node.js is vulnerable to remote code execution.
CVE-2026-111497 (high): A Node.js process that decompresses attacker-controlled Brotli data can be made to leak memory or run arbitrary code.
You’re exposed if your app or a library decompresses bad Brotli data (e.g. the built-in fetch(), body-parser)
Aikido detects this. Patches are available.
Yoo Teknium continues to cook fine meals for the Hermes crew.
🚨 HERMES CAN LEARN A WEBSITE BY WATCHING YOU USE IT.
A new plugin lets you record yourself performing a browser workflow, then use /learn to turn it into a reusable skill.
SHOW IT ONCE. TEACH IT FOR GOOD.
Merged today.
This is cool AF, @Teknium! 🔥🪽
GE is honestly the greatest.
If you’ve played games on Linux and thought to yourself “wow this works better than it did on windows” That’s largely thanks to this guy.
FPS looking much better now, still making some tweaks but it's running WAY better than it originally was. (again, this is -not- using xenia's gpu translator). Xenia reads the low-level command stream the game sends to the Xbox 360 GPU and emulates that GPU in Vulkan. Our renderer captures the game's Direct3D calls instead and renders the scene directly with native Vulkan render targets, closer to how DXVK translates Windows D3D games than to how an emulator works. This is running upscaled at 4k -- no FSR yet.
I really need to give Hermes kanban another shot for long running tasks.
It seems maybe kanban style setups have the advantage that a lot of the Information needed to complete the task is held in the profile architecture/ kanban interface itself.
It doesn’t need the AI to understand the separation of concerns it at runtime.
It’s existence on a persistent layer makes it resilient to the pitfalls that you might run into while relying on a single agent to delegate at runtime.
More so with long tasks than short.
SALT 🎸 retweeted
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 🏴
Only a few prompts into using this model and it’s really nice. Going to keep working on my custom skate3 recomp with it today and see how it works.
Aloha!🌺 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast
Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!!
Open weights under the MIT license.
Coding
✅SWE-bench Verified: 0.845
✅TB2.1: 0.813
✅CyberGym: 0.800
✅NL2Repo: 0.512
Agentic
✅HLE: 0.446
✅BrowseComp: 0.785
✅MCP-Atlas: 0.746
✅Toolathlon: 0.708
🤗Hugging Face: huggingface.co/ornith-ai/Orn…
We can’t wait to see what you build with Ornith-1.5-122B.
Hmmmm what do we have here.
Aloha!🌺 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast
Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!!
Open weights under the MIT license.
Coding
✅SWE-bench Verified: 0.845
✅TB2.1: 0.813
✅CyberGym: 0.800
✅NL2Repo: 0.512
Agentic
✅HLE: 0.446
✅BrowseComp: 0.785
✅MCP-Atlas: 0.746
✅Toolathlon: 0.708
🤗Hugging Face: huggingface.co/ornith-ai/Orn…
We can’t wait to see what you build with Ornith-1.5-122B.
I run a super intelligent AI at home for a fraction of this.
What it takes to power my longevity home for 1 day
. 15 kWh 200°F sauna
. 15 kWh evening AC for sleep temp 67°F
. 10 kWh five air purifiers
. 3 kWh eight sleep bed
. 2 kWh HBOT
. 2 kWh daylight devices
. 2 kWh red light therapy
. 1 kWh kate's night time erection device
. 1 kWh reverse osmosis water
. 1 kWh IHHT
Totals
. 52 kWh for longevity
. 93 kWh for whole house
. 64 kWh solar generation
. 33 kWh exported to the grid
A kWh is about 80 full phone charges
So about 4,200 phone charges to power my longevity protocol each day
