←
Paolo Stagno (VoidSec)1,832 posts
Paolo Stagno (VoidSec) avatar

Paolo Stagno (VoidSec)

@Void_Sec

Vulnerability Researcher and Exploit Developer. LLM whisperer. Former CTO and Director of Research @Crowdfense, ex-@XI_Research.

◷ Joined November 2013▧ 241 Photos and videos
Paolo Stagno (VoidSec) avatar
Paolo Stagno (VoidSec)@Void_Sec·Nov 6

Rack update, added two fans and capped the GPU clock at 2200. To be honest the cap alone does the heavy lifting with minimal performance hit.

Post attachment
Paolo Stagno (VoidSec) avatar
Paolo Stagno (VoidSec)@Void_Sec·Nov 6

I asked GPT to quantify how much I 'd have paid in API token costs for my last 15 days of work on my DGX Spark cluster. Turns out, A LOT. The cluster is already paying for itself, especially considering that the cybersecurity work I did would have been blocked on frontier models

Post attachment
Paolo Stagno (VoidSec) avatar
Paolo Stagno (VoidSec)@Void_Sec·Nov 3

I'll give frontier models two weeks before they'll introduce guardrails preventing direct weights changes

We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…

Post attachment
Paolo Stagno (VoidSec) avatar
Paolo Stagno (VoidSec)@Void_Sec·Oct 29

I'd take 4x DGX Sparks over a MAC Studio any time. Prefill performance on huge context and long horizon runs alone. CUDA and its mature ecosystem for image/video generation and the flexibility to run multiple LLMs independently split across nodes.

Paolo Stagno (VoidSec) avatar
Paolo Stagno (VoidSec)@Void_Sec·Oct 24

Netflix made us forget about torrents, Hugging Face did the same for model weights. But, as uncensored and abliterated models are quietly disappearing, we're learning the same lesson again: time to seed.

Paolo Stagno (VoidSec) avatar
Paolo Stagno (VoidSec)@Void_Sec·Oct 20

That might be huge

🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable. 🔗 github.com/deepseek-ai/DeepI… 1/4

Paolo Stagno (VoidSec) avatar
Paolo Stagno (VoidSec)@Void_Sec·Oct 16

In case anyone’s wondering, the benchmark was run using a ring topology, as I don’t currently have a switch to connect all four DGX Sparks