Vyber07/cyber-security
Viewer • Updated • 1 • 22.5k • 1.07k
x
invincibilul
AI & ML interests
None yet
Recent Activity
liked a dataset about 1 hour ago
Vyber07/cyber-security new activity about 1 hour ago
unsloth/DeepSeek-V4.1-Flash-1017-GGUF:how good is this q1 liked a model about 1 hour ago
MoonMath-ai/DeepSeek-V4.1-Flash-1017-uncensoredOrganizations
None yet
liked a
dataset about 1 hour ago
how good is this q1
#19 opened about 1 hour ago
by invincibilul
liked 2
models about 1 hour ago
reacted to danielhanchen's post with 🔥 2 days ago
Post
7,736
Today, we're releasing the highest accuracy Qwen3.8-27B GGUFs!
Our new Dynamic V3.1 GGUFs lead by 5–10% on average across Terminal Bench, DeepSWE & more. We’re working on an even better version for Qwen4.
Run on 12GB RAM setups
GGUF: unsloth/Qwen3.8-27B-GGUF
Blog: https://unsloth.ai/docs/models/qwen3.8
Our new Dynamic V3.1 GGUFs lead by 5–10% on average across Terminal Bench, DeepSWE & more. We’re working on an even better version for Qwen4.
Run on 12GB RAM setups
GGUF: unsloth/Qwen3.8-27B-GGUF
Blog: https://unsloth.ai/docs/models/qwen3.8
liked a
model 3 days ago
liked a
model 5 days ago
liked 2
models 10 days ago
reacted to SeaWolf-AI's post with 👍 12 days ago
Post
5,796
🛑 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):
FINAL-Bench/ViKernel-Desktop
Try it in 30 seconds: press 🛑 KILL, type
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):
FINAL-Bench/ViKernel-Desktop
Try it in 30 seconds: press 🛑 KILL, type
run weather (refused), then resume --key vikernel-demo. liked a
model 13 days ago
liked 2
models about 2 months ago
How does it compare to huihui
👍🤗 2
4
#40 opened 2 months ago
by 
blbx42
liked 6
models 2 months ago
XHToken/Spark-X2.5-4B
Text Generation • 4B • Updated • 8.3k • 1.44k
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF
Image-Text-to-Text • 27B • Updated • 1.34M • 2.83k
nvidia/Qwen3.8-Flash-Next-NVFP4
Image-Text-to-Text • 120B • Updated • 86.4k • 460
orcarouter/GLM-5.3-Flash-Uncensored-GGUF
Image-Text-to-Text • 321B • Updated • 19.8k • 177
zai-org/GLM-5.3
Text Generation • 753B • Updated • 1.76M • • 2.45k
Qwen/Qwen3.8-Flash-Next
Image-Text-to-Text • 180B • Updated • 3M • • 7.14k