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.
0
0
10
849
I'll be extremely curious to see Anthropic's exploit for CVE-2026-98432 working remotely
1
1
21
1,823
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
The cluster is already paying for itself, especially considering that the cybersecurity work I did would have been blocked on frontier models
14
2
33
3,652
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: fronely read/write neural network weights! 🧵
Blog: rikiyat.github.io/blog/weight-sp…Community noteLLM 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.…
0
0
5
788
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.
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.
0
0
7
796
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.
But, as uncensored and abliterated models are quietly disappearing, we're learning the same lesson again: time to seed.
2
0
11
1,029
So now it's Flare vs DeepInfer
github.com/NVIDIA/flare-l…
github.com/NVIDIA/flare-l…
0
0
3
787
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/De…
1/4
0
0
3
770
Looks like even though I just finished setting up my local model pipeline, there's always something new to test. huggingface.co/deepseek-ai/De…
2
0
8
771
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
0
0
2
236
I don't understand the hype/excitement around Nemotron 3.5, when Qwen3.8 Flash Next beats it on all the benchmarks...
0
0
2
777
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
7
5
40
3,900
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-R7Sm…
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-R7Sm…
33
80
427
46,118
That's crazy
This looks like this could be exactly what I'm investigating. Anyone affected, please contact me or open your ledger and send me pictures so we can confirm if there's a bug in there (pictures: ledger board on top, spy implant below).
x.com/Ledger_Support…
0
0
14
1,689
Amazing how offensive work "is for organizations only; individual researchers are not eligible."
Local AI is the way to go. Not going to renew @AnthropicAI.
Local AI is the way to go. Not going to renew @AnthropicAI.
We’re expanding our Cyber Verification Program to give security professionals broader access to our most capable models.
Through this program, verified security professionals can access Claude Mythos 5.1, Opus 5.5, and Sonnet 5.5 with safeguards designed for defensive work.
We’re also opening up new tiers to allow for authorized offensive work, like penetration testing and red-teaming.
anthropic.com/news/cyber-ver…
3
5
40
2,130
So NVIDIA announces 64GB DGX Spark configuration at the original price of the 128GB ones; makes perfect sense to me blogs.nvidia.com/blog/local-ai-…
0
0
3
652