
Vulnerability Researcher and Exploit Developer. LLM whisperer. Former CTO and Director of Research @Crowdfense, ex-@XI_Research.
ntoskrnl.exe
Joined November 2013
- Tweets1.8K
- Following2K
- Followers5.3K
- Likes3.2K
Remember when a critical vulnerability meant you could actually get RCE?
Now it feels like every new *2Shell requires perfectly aligned planets, 17 non-default configurations, and a blood sacrifice to reproduce.
Can we just go back to bugs that are just... exploitable?
So, let me get it straight, the NVIDIA DGX spark development kit it's just the usual 4 spark connected in ring topology!?
blogs.nvidia.com/blog/dgx-sp…
1
2
754
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.
10
887
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
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…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
5
807
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.
7
808
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.
2
11
1,036
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
3
775
Looks like even though I just finished setting up my local model pipeline, there's always something new to test. huggingface.co/deepseek-ai/D…
2
8
776
I don't understand the hype/excitement around Nemotron 3.5, when Qwen3.8 Flash Next beats it on all the benchmarks...
2
781
While reverse engineering down to 1:1 of the original code has always been possible (despite taking skills and a lot of time), I believe the current advancement with AI will push more and more vendors to ship heavily obfuscated and DRM protected code
Paolo Stagno (VoidSec) retweeted
How to recognize the implants you can find on a Ledger Nano X today?
Learn about the Ledger Nano X display test pads, which one is the most important to watch for, and what today's known implants look like.
youtube.com/watch?v=A-R7Sm0E…








