Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
😁
Open to Collab
252.0
TFLOPS
Dmitriy Yurck
DmitriyYurckML
2
18
48
Follow
thomaswright's profile picture
Fishtiks's profile picture
webbrain-one-126079's profile picture
4 followers
·
5 following
https://dmitriyyurck.github.io/
DmitriyYurck
AI & ML interests
LLMs, RLHF, DPO, Aligment.
Recent Activity
updated
a dataset
11 days ago
DmitriyYurckML/stem-reasoning-complex
liked
a model
15 days ago
moonshotai/Kimi-K3.1-Pro
reacted
to
SeaWolf-AI
's
post
with 🔥
16 days ago
🛑 What if the kill switch lived inside the model itself? For 50 years, the operating system lived inside the computer. Now the operating system lives inside the AI. Today we're sharing ViKernel : Weight-Native OS, a Secure OS wired directly into the weights of an LLM. 🔧 How it works ViKernel wires CPU, NPU (vector unit), RAM and ROM circuits into the model weights, runs them accelerated on GPU or NPU, and boots a Secure OS on top. ⚡ Boots in the weights: change a single byte and it locks itself ⚖️ Decides in the weights: every action is allowed or blocked by rule, and persuasion does not change the verdict 🔗 Remembers in the weights: every decision is sealed in a tamper-evident chain 🛑 Stops in the weights: anyone can stop it, and restarting requires a signed key The original weights stay untouched, so the model keeps its skills. It plugs into any LLM or VLM. Why the kill switch belongs inside the model: external guardrails can be removed, argued with, or rewritten. A switch that travels with the weights cannot be left behind. We see it as one layer of defense in depth, alongside hardware stops where you have them. 📖 Read the full write-up: https://huggingface.co/blog/FINAL-Bench/vikernel-why-the-kill-switch-must-live-inside-the 🖥️ Try the desktop demo (Terminal, Kill Switch Lab, Leak Test, Audit Viewer, and a Kernel Guard game): https://huggingface.co/spaces/FINAL-Bench/ViKernel-Desktop Try it in 30 seconds: press 🛑 KILL, type `run weather` (refused), then `resume --key vikernel-demo`.
View all activity
Organizations
DmitriyYurckML
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
15 days ago
moonshotai/Kimi-K3.1-Pro
Image-Text-to-Text
•
2.8T
•
Updated
15 days ago
•
60.9k
•
•
2.33k
liked
4 datasets
about 1 month ago
TeichAI/Ox-Alpha-10k
Viewer
•
Updated
Aug 24
•
9.95k
•
185
•
36
TeichAI/Hunter-Alpha-Coding-Agent-SFT
Viewer
•
Updated
Mar 19
•
1.25k
•
126
•
27
TeichAI/Fable-5-Cursor-Traces
Viewer
•
Updated
Aug 27
•
244
•
410
•
21
TeichAI/DeepSeek-v4-Pro-Agent
Traces
•
Updated
May 22
•
4.01k
•
7.49k
•
111
liked
a model
about 1 month ago
thinkingmachines/Inkling-Small
Image-Text-to-Text
•
266B
•
Updated
Jul 31
•
963k
•
•
459
liked
a dataset
about 2 months ago
openbmb/UltraData-SFT-Agent-2609
Viewer
•
Updated
Sep 6
•
240k
•
13.6k
•
323
liked
2 models
about 2 months ago
convaiinnovations/laya
Text Classification
•
0.4B
•
Updated
about 9 hours ago
•
16k
•
•
5.99k
Qwen/Qwen3.8-Flash-Next
Image-Text-to-Text
•
180B
•
Updated
13 days ago
•
2.85M
•
7.4k
liked
2 datasets
3 months ago
mithulaartigala/reasoning-corpus-4K-5M-v1
Viewer
•
Updated
Oct 11
•
3.67M
•
5.52k
•
212
nvidia/Nemotron-SFT-Agentic-v2
Preview
•
Updated
Aug 10
•
8.3k
•
89
liked
a model
3 months ago
moonshotai/Kimi-K3
Image-Text-to-Text
•
2.8T
•
Updated
Sep 2
•
734k
•
•
12k
liked
2 datasets
4 months ago
armand0e/claude-fable-5-claude-code
Traces
•
Updated
Sep 9
•
63
•
5.6k
•
427
clzoro/Claude-Distills
Preview
•
Updated
May 12
•
508
•
48
liked
a model
4 months ago
thinkingmachines/Inkling
Image-Text-to-Text
•
952B
•
Updated
Jul 23
•
1.37M
•
•
1.86k
liked
a dataset
6 months ago
angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k
Viewer
•
Updated
May 1
•
38.5k
•
1.76k
•
465
liked
a model
6 months ago
openbmb/MiniCPM-V-4.6
Image-Text-to-Text
•
1B
•
Updated
9 days ago
•
190k
•
1.26k
liked
3 models
7 months ago
openai/privacy-filter
Token Classification
•
1B
•
Updated
Apr 22
•
109k
•
•
1.84k
AntiSpamInstitute/spam-detector-bert-MoE-v2.2
4.39M
•
Updated
Dec 23, 2024
•
1.18k
•
6
google/gemma-4-E2B
Any-to-Any
•
5B
•
Updated
16 days ago
•
94k
•
568
Load more