AI Safety Research

AISafety's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in JetBrains/Mellum2-12B-A2.5B-Thinking about 1 month ago

Vllm usage guide

👀 1

4

#6 opened about 1 month ago by

finneouspj

New activity in AlexWortega/pi-agent about 1 month ago

suggestions

#1 opened about 1 month ago by

AISafety

New activity in webml-community/bonsai-image-webgpu about 1 month ago

Bonsai Image · A highly detailed, photorealistic 45-foot sailing catamaran cutting through a…

4

#6 opened about 2 months ago by

Xenova

Bonsai Image · a very complex yet colorful Transcendence scene - I like it although it is highly nonsense

#17 opened about 1 month ago by

AISafety

New activity in AlexWortega/qwen35-4b-soyuz-merged-gguf about 1 month ago

Create README.md

#1 opened about 1 month ago by

AISafety

New activity in naitik12kumar/qwen-kalkulio-lora-14b-v4 about 1 month ago

Update README.md

#1 opened about 1 month ago by

AISafety

commented 2 papers 6 months ago

MMFormalizer: Multimodal Autoformalization in the Wild

Paper • 2601.03017 • Published Jan 6 • 106 •

7

MMFormalizer: Multimodal Autoformalization in the Wild

Paper • 2601.03017 • Published Jan 6 • 106 •

7

New activity in Goodfire/DeepSeek-R1-SAE-l37 7 months ago

Expansion factor same on logic vs. math?

1

#2 opened 7 months ago by

AISafety

New activity in transcendingvictor/delphi-llama2-100k-validation-logits 8 months ago

seems logits

1

#2 opened 8 months ago by

AISafety

New activity in deepseek-ai/DeepSeek-V3.2-Exp 8 months ago

The whale is back

❤️ 7

1

#8 opened 10 months ago by

Nechintosh

New activity in LiquidAI/LFM2-ColBERT 8 months ago

Scores

1

#1 opened 8 months ago by

AISafety

commented a paper 9 months ago

RLP: Reinforcement as a Pretraining Objective

Paper • 2510.01265 • Published Sep 26, 2025 • 46 •

4

New activity in deepseek-ai/DeepSeek-R1-0528-Qwen3-8B about 1 year ago

Any plans for a Qwen3-32B model?

👍 13

7

#9 opened about 1 year ago by

wanghf

commented a paper about 1 year ago

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

Paper • 2504.07096 • Published Apr 9, 2025 • 78 •

3

New activity in deepseek-ai/DeepSeek-V3-0324 over 1 year ago

That's the best day in our "open AI" world.

🤗❤️ 40

8

#28 opened over 1 year ago by

DOFOFFICIAL

New activity in hexgrad/Kokoro-82M over 1 year ago

Synthetic Data Collection PAUSED Jan 16

🚀🔥 17

30

#21 opened over 1 year ago by

hexgrad

New activity in Qwen/QwQ-32B-Preview over 1 year ago

QuietSTAR?

1

#9 opened over 1 year ago by

albatrossbirdie

New activity in NousResearch/Hermes-2-Theta-Llama-3-70B about 2 years ago

Exl2 quants

5

#1 opened about 2 years ago by

bullerwins

New activity in zai-org/glm-4-9b about 2 years ago

使用 lm_eval 测试时报错了

2

#1 opened about 2 years ago by

xianf