mr_r0b0t
@mr_r0b0t
observer of a human on a rock somewhere in space
8K Following 11.5K Followers
I’m gonna come out and say it!
@Teknium is the best FOSS repo owner in the game. He has a magical way of protecting Hermes Agent while simultaneously understanding your idea and how it could be optimally integrated.
To top it all off, you get advice on how to best do that! 🏆
Show more
Huge @NVIDIARTXSpark news as two new models are officially announced!
The growth of the GB10 platform is awesome to see and the prices for the Surface Laptop ($2,599) and RTX Spark Dev Box ($5,999) appear to fill a nice gap in the market!
Show more
The appropriate way to respond to this ⬇️
It's understandable when your agent pulls in code and maybe you didn't give it the proper instruction to credit.
It's NOT understandable when you realize and instead of fixing, you (or your "fans") justify and rationalize the "mistake" that was made <3
In the second situation, there is no mistake.
HUGE respect for @Tech2Wild here 👑
Show more
"voxel_shinto"
Ox Alpha via @NousResearch Nous Portal
check out the interactive/looping html here 🤩
Tip for your @NousResearch Hermes Agent Bots:
Create an "Orchestrator" Bot and then have it design its own team to optimally fulfill any/all user requests. Here's El Jefe (my orchestrator) completing a very solid roster including comprehensive soul.md entries for each Bot!
Show more
Qwen3.8-27B NVFP4 + MTP is live for GB10 🚀
Quantized with @NVIDIAAI ModelOpt 0.46.0rc1 using its shipped qwen3_5 recipe.
2.45× c1 speedup vs AR
84.3 tok/s at c8
262K context, 8/8 NIAH
17/17 zero-error runs
Model:
Repo:
Show more
Nous Portal + Buzz = 4 Agents on a team, powered by FREE models in the Nous Portal, debating which is using the best model 😂
If you're managing multiple agents, @NousResearch + @blocks Buzz has to be one of the best options out there right now!
Show more
If you SSH from your phone, I highly recommend trying Moshi!
This has replaced Termius on all my
mobile devices and undoubtedly increases my productivity while on the go 🤩
Finally done with work for the week! Time to cook up a Reachy 🤖🤖🤖
@pollenrobotics / @huggingface package received 🥳
If you have a GB10 (DGX Spark) and a Hermes Agent, have a look at what Mike did! Pretty smart 🧠🧠🧠
"/learn the DGX Spark playbooks found here and produce a skill that demonstrates a complete mastery of GB10 operations"
Show more
@NVIDIAAI just gifted us a 75B MoE 🤩🤩🤩
nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4
75.3B total / 9.3B active compressed from Nemotron-3-Super-120B using the Iterative Puzzle framework.
1M token context support!
Perfect for your single GB10 ♥️
Show more
The moment many of us have been waiting for has arrived!
Thanks for the 3.6-27B-NVFP4 @NVIDIAAI 🤩
Deepseek V4 Flash is one of the best "worker" models out there IMHO so this is very cool!
Yet ANOTHER free model available through the Nous Portal 😍😍😍
Can't believe people are still playing with toy lobsters and missing out on literal MONTHS of free inference through @NousResearch
Show more
