AISafety (AI Safety Research)

liked 2 models 6 days ago

Qwen/Qwen3.8-Flash-Next

Image-Text-to-Text • 180B • Updated 9 days ago • 351k • 4.88k

mitkox/Huihui-Qwen3.8-27B-abliterated-Q4_K_M-GGUF

Image-Text-to-Text • 27B • Updated 20 days ago • 5.25k • 4

liked a model 9 days ago

zai-org/GLM-5.3-Flash

Image-Text-to-Text • 321B • Updated about 19 hours ago • 655k • • 2.05k

liked 2 models 10 days ago

nvidia/GR00T-N1.7-3B

Robotics • 3B • Updated Apr 23 • 79.5k • 120

nvidia/GR00T-H-N1.7

3B • Updated May 30 • 501 • 7

liked a model 14 days ago

ornith-ai/Ornith-1.5-35B-A3B

Text Generation • 36B • Updated 13 days ago • 257k • 542

commented a paper 15 days ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published 18 days ago • 158 •

6

liked a dataset 18 days ago

aisleinc/HoF-Bench

Viewer • Updated Jul 22 • 285 • 254 • 5

upvoted a collection 19 days ago

💧 LFM2.5

Collection

Collection of post-trained and base LFM2.5 models. • 16 items • Updated Aug 4 • 219

liked a Space 24 days ago

HF Realtime Voice

🎙

553

Realtime voice over WebSocket or WebRTC

upvoted an article 26 days ago

Article

Borealis — open data, code, weights recipe for training Audio LLM

AlexWortega

•

May 25

• 16

liked a model 28 days ago

amd/Instella-MoE-16B-A3B-SFT

Text Generation • 16B • Updated 2 days ago • 1.21k • 11

upvoted a collection 28 days ago

Instella-MoE ✨

Collection

Family of fully open 16B MoE LLM with 2.8B active params per token, trained on AMD Instinct™ MI300 & MI325 GPUs. • 6 items • Updated Jul 28 • 19

liked a model 29 days ago

SyzygyResearch/Mach-1-Additive-35B

Updated 18 days ago • 3.64k • 128

New activity in AlexWortega/universal-nla-v24-dirfix about 1 month ago

correct to a working Github link

#1 opened about 1 month ago by

AISafety

liked 2 models about 1 month ago

Nanbeige/Nanbeige4.2-3B

Text Generation • 4B • Updated 10 days ago • 34.3k • 740

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 3 days ago • 2.64M • • 11.2k

commented on Security incident disclosure — July 2026 about 1 month ago

It's just responsible disclosure, the sandboxing package repository likely was deployed elsewhere and needs fixing before the details get published and exploits get tried out.

commented on Security incident disclosure — July 2026 about 1 month ago

No doubt they've borrowed here and there, but you seem psychotic and Hanlon's Razor seems more fitting here.
( https://umbrex.com/resources/tools-for-thinking/what-is-hanlons-razor/ )

liked a Space about 1 month ago

Reproducing ICML 2026

🔬

218

Reproduce every ICML 2026 paper with your agent

AI Safety Research

AI & ML interests

Recent Activity

Organizations