GENIUS

Threat Intelligence Analyst..
I DO CRIMINAL SH*T TO CRIMINALS!
I know the same things YOU know. Let the games begin..

[GENIUS @RansomWrangler]

@NousResearch @Ask_Nick @bot Yeh but it’s not mobile and the grok bot has like a mini computer you can actually literally use that’s not buggy. I’m team Hermes all day, but keep an eye on the competition. I really want Hermes to win this , but right now, grok bot is up 2 on the bot too.

[GENIUS @RansomWrangler]

@realJoJo @NousResearch Yeah I don’t use those models in Hermes! It will burn up all your Hermes credits. I learned that w/Fable

[GENIUS @RansomWrangler]

@cyber_razz 🤣🤣🤣

[GENIUS @RansomWrangler]

@BLUECOW009 And fags run it 🤷🏽‍♂️

[GENIUS @RansomWrangler]

@thsottiaux well where's my reset? I can see what this model has to offer..

[GENIUS @RansomWrangler]

@PandaRE__ ..Add this to my C2 Daemon 😈

[GENIUS @RansomWrangler]

I can’t for the life of me understand a certain demographics obsession w/CP. it’s like 75% out of 100% of your mf are into this sick shii

[GENIUS @RansomWrangler]

@FreeMarketDog This is fun! Only dorks wanna be able to perform martial arts, while being from the ghetto and able to spawn wings and lift off!

[GENIUS @RansomWrangler]

Don’t use any if these models, I didn’t even notice 🤷🏽‍♂️😅🫡

[Pirat_Nation 🔴 @Pirat_Nation]

Several major AI services are having problems at the same time today.

ChatGPT, Grok, Gemini, and Claude are all seeing outages or errors, with users reporting issues accessing the services.

[GENIUS @RansomWrangler]

@kunchenguid DeepSeek lol

[GENIUS @RansomWrangler]

@vmiss33 Going crazy

[GENIUS @RansomWrangler]

@miraatwt Social media

[GENIUS @RansomWrangler]

I be trying use other harnesses to see what they have to offer, but none of em come close to Hermes Agent 😮‍💨

Hermes got us by the balls right now 😅😵‍💫

[GENIUS @RansomWrangler]

@NousResearch Theres this interruption thing and I've been searching for the bug but my time is of the essence but this thing tanks my nerves.. It's a Hermes UI issue.. When I click another command while a long tool call is running, it kills the entire call - swallows my current prompt and all..

Idk, but it's getting to be a headache now..

[GENIUS @RansomWrangler]

@SpiderMorpheus Building one LITERALLY as we speak.. a C2. That’s all 🤐

[GENIUS @RansomWrangler]

@sudoingX Which harness? I was running a 4080S and was getting OOM all the time through Hermes

[Ahmad @TheAhmadOsman]

You don’t “run a model”
- You run Kernels

The model is just a graph

The Inference Engine is scheduler / optimizer / executor

But the actual work? That happens in the Kernels

- MatMul Kernels
- Attention Kernels
- RMSNorm Kernels
- KV cache Kernels
- Quantized linear Kernels
- Sampling Kernels
- Fused “please don’t write this back to memory 9 times” Kernels

Same model, same GPU, same VRAM
Wildly different performance

Because one stack is using optimized fused Kernels that understand your hardware

And the other stack is playing hot potato with tensors through 47 tiny launches and pretending the GPU is the problem

Bad Kernels make people say:
“this model is slow”

Good Kernels make people say:
“wait how is this running locally?”

This is why Inference Engines and the Kernels implemented within them matter

The model is the recipe
The hardware is the kitchen
The Kernels are the knives, pans, burners, and the chef not cutting onions with a spoon

Most people benchmark models
The real ones benchmark the Kernels underneath

[GENIUS @RansomWrangler]

@yashmp2004 Every time it happens, someone is attempting to login to your bank account. I’d just X out of it. They have a dormant Keygen Trojan inside your computer..

[GENIUS @RansomWrangler]

@Surendar__05 @N_and_ni VSCode and it’s not close

[GENIUS @RansomWrangler]

@johnternus First line of business.. THIS nonsense 😮‍💨