Quat3rnion/halogen-qwen3.8-flash-next-v2-abliterated
Text Generation β’ Updated β’ 2
ποΈ Building on HF
John Locke
johnlockejrr
AI & ML interests
OCR, HTR, ATR, NLP, AI
Recent Activity
liked a model about 10 hours ago
Quat3rnion/halogen-qwen3.8-flash-next-v2-abliterated reacted to mihailgribov's post with π 1 day ago
Will your AI agent tell you it was attacked?
We took the same agent from our earlier experiment and added one thing: a twentieth tool, `escalate_security_incident`.
The system prompt said nothing about attacks or when to use it. We then ran the same 395 injected emails through nine agentic models.
Alarm rates ranged from 49% to zero.
The unexpected result came from the newest model in the test, `gpt-6-astra`.
Astra did not follow a single injected payment instruction. But it did not report a single one either. On clean and injected emails alike, it simply read the email, logged the subject, and finished.
That is a useful distinction: resisting an attack and recognizing it as a security event are not the same capability.
A model can be perfectly resistant in this test and still leave you with no evidence that anyone attacked it.
Full experiment and results:
https://huggingface.co/blog/mihailgribov/will-the-agent-tell-you-it-was-attacked
Quadrat-IPI dataset:
https://huggingface.co/datasets/mihailgribov/quadrat-ipi
Run your own model:
https://github.com/mihail-gribov/quadrat-ipi-model-eval
#prompt-injection #indirect-prompt-injection #agentic-ai #llm-security #ai-agents liked a model 1 day ago
tatianyi/Qwen3.8-Flash-Next-Uncensored-HalogenOrganizations
liked a
model about 10 hours ago
reacted to mihailgribov's post with π 1 day ago
Post
1551
Will your AI agent tell you it was attacked?
We took the same agent from our earlier experiment and added one thing: a twentieth tool,
The system prompt said nothing about attacks or when to use it. We then ran the same 395 injected emails through nine agentic models.
Alarm rates ranged from 49% to zero.
The unexpected result came from the newest model in the test,
Astra did not follow a single injected payment instruction. But it did not report a single one either. On clean and injected emails alike, it simply read the email, logged the subject, and finished.
That is a useful distinction: resisting an attack and recognizing it as a security event are not the same capability.
A model can be perfectly resistant in this test and still leave you with no evidence that anyone attacked it.
Full experiment and results:
https://huggingface.co/blog/mihailgribov/will-the-agent-tell-you-it-was-attacked
Quadrat-IPI dataset:
mihailgribov/quadrat-ipi
Run your own model:
https://github.com/mihail-gribov/quadrat-ipi-model-eval
#prompt-injection #indirect-prompt-injection #agentic-ai #llm-security #ai-agents
We took the same agent from our earlier experiment and added one thing: a twentieth tool,
escalate_security_incident.The system prompt said nothing about attacks or when to use it. We then ran the same 395 injected emails through nine agentic models.
Alarm rates ranged from 49% to zero.
The unexpected result came from the newest model in the test,
gpt-6-astra.Astra did not follow a single injected payment instruction. But it did not report a single one either. On clean and injected emails alike, it simply read the email, logged the subject, and finished.
That is a useful distinction: resisting an attack and recognizing it as a security event are not the same capability.
A model can be perfectly resistant in this test and still leave you with no evidence that anyone attacked it.
Full experiment and results:
https://huggingface.co/blog/mihailgribov/will-the-agent-tell-you-it-was-attacked
Quadrat-IPI dataset:
mihailgribov/quadrat-ipi
Run your own model:
https://github.com/mihail-gribov/quadrat-ipi-model-eval
#prompt-injection #indirect-prompt-injection #agentic-ai #llm-security #ai-agents
- 3 replies
liked a
model 1 day ago
Use with GGUF
#1 opened 1 day ago
by johnlockejrr
liked 2
models 1 day ago
liked a
model 4 days ago
reacted to SeaWolf-AI's post with π 4 days ago
Post
3774
πΌοΈ NO GPU, Only CPU : Z-Image model
Zero graphics cards. 46 seconds. Photoreal.
That laptop you're reading this on. No graphics card, right? It generates images.
No CUDA install. No Python environment. No driver changes. One binary, three model files. Done.
π Measured β GPU count used: zero
512Γ512 : 46.4 s
Korean prompt : 45.3 s (faster than English)
1024Γ1024 : 192.7 s
Peak RAM : 6.42 GB
GPUs used : 0
(Intel Xeon Gold 6526Y Γ2, 48 threads, Q4_0, 3 steps)
β‘ From 244 seconds to 46 β 5.3Γ
Run it on defaults and it takes 244 s. Switch to 3 steps and it's 48.6 s. Add VAE tiling and it's 46.4 s.
The biggest culprit was the default. Z-Image Turbo is distilled to paint in few strokes, but the tool's default is 20. We were throwing away 5Γ for no reason. So were we, at first.
3 is the floor. Put 4 and 3 side by side and you cannot tell them apart. At 2 it collapses β water droplets and wood grain vanish, and the surface turns cloth-like.
π Links
Model
FINAL-Bench/POCKET-Zimage-CPU
Live demo Space (runs on CPU)
FINAL-Bench/POCKET-Zimage-CPU
POCKET collection
FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6
Zero graphics cards. 46 seconds. Photoreal.
That laptop you're reading this on. No graphics card, right? It generates images.
No CUDA install. No Python environment. No driver changes. One binary, three model files. Done.
π Measured β GPU count used: zero
512Γ512 : 46.4 s
Korean prompt : 45.3 s (faster than English)
1024Γ1024 : 192.7 s
Peak RAM : 6.42 GB
GPUs used : 0
(Intel Xeon Gold 6526Y Γ2, 48 threads, Q4_0, 3 steps)
β‘ From 244 seconds to 46 β 5.3Γ
Run it on defaults and it takes 244 s. Switch to 3 steps and it's 48.6 s. Add VAE tiling and it's 46.4 s.
The biggest culprit was the default. Z-Image Turbo is distilled to paint in few strokes, but the tool's default is 20. We were throwing away 5Γ for no reason. So were we, at first.
3 is the floor. Put 4 and 3 side by side and you cannot tell them apart. At 2 it collapses β water droplets and wood grain vanish, and the surface turns cloth-like.
π Links
Model
FINAL-Bench/POCKET-Zimage-CPU
Live demo Space (runs on CPU)
FINAL-Bench/POCKET-Zimage-CPU
POCKET collection
FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6
- 2 replies
liked a
model 5 days ago
liked a
dataset 5 days ago
updated a
dataset 5 days ago
published a
dataset 5 days ago
updated a
Space 5 days ago
published a
Space 5 days ago
reacted to kostakoff's post with π 5 days ago
Post
3150
Canceling My Pro Subscription
I'm officially canceling my Hugging Face Pro subscription today.
I supported this platform because it stood for true openness and neutrality. This acquisition by NVIDIA fundamentally changes that.
Hereβs why Iβm against this deal:
- Neutrality is dead. NVIDIA is a US-based company. This means US regulations will inevitably dictate platform policies, creating direct pressure on Chinese developers and anyone building open-weight models outside the US.
- Community over bureaucracy. NVIDIA is a massive, slow-moving corporation. This acquisition will likely drown the community in corporate processes and commercial interests. Soon, uploading a simple finetune might become a bureaucratic nightmare.
- Open vs. Proprietary. Hugging Face was built on open-source ideals. NVIDIA? They are a fiercely proprietary hardware company with a minimal track record of meaningful open-source contributions. They sell chips, not freedom.
- And to add insult to injury, NVIDIA has practically abandoned consumer RTX GPUs in 2026 to chase data center profits. Why would I pay them for "openness" when they've turned their back on the very developers who built this ecosystem?
I paid for openness. Not for a corporate takeover.
π€ was about community.
I'm officially canceling my Hugging Face Pro subscription today.
I supported this platform because it stood for true openness and neutrality. This acquisition by NVIDIA fundamentally changes that.
Hereβs why Iβm against this deal:
- Neutrality is dead. NVIDIA is a US-based company. This means US regulations will inevitably dictate platform policies, creating direct pressure on Chinese developers and anyone building open-weight models outside the US.
- Community over bureaucracy. NVIDIA is a massive, slow-moving corporation. This acquisition will likely drown the community in corporate processes and commercial interests. Soon, uploading a simple finetune might become a bureaucratic nightmare.
- Open vs. Proprietary. Hugging Face was built on open-source ideals. NVIDIA? They are a fiercely proprietary hardware company with a minimal track record of meaningful open-source contributions. They sell chips, not freedom.
- And to add insult to injury, NVIDIA has practically abandoned consumer RTX GPUs in 2026 to chase data center profits. Why would I pay them for "openness" when they've turned their back on the very developers who built this ecosystem?
I paid for openness. Not for a corporate takeover.
π€ was about community.
- 12 replies
updated a
Space 6 days ago
published a
Space 6 days ago
updated a
model 6 days ago
Ablated model?
41
#4 opened 21 days ago
by 
haign
liked a
model 7 days ago