AI Safety Research

AISafety

·

https://humanaligned.ai

AI & ML interests

LLMs, planning, EA

Recent Activity

liked a model 1 day ago

satgeze/GLM-5.3-Flash-EXL3-TR3-3.5bpw

liked a model 3 days ago

prism-ml/Ternary-Bonsai-27B-gguf

liked a model 4 days ago

yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF

View all activity

Organizations

commented a paper about 1 month ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published Aug 18 • 160 •

New activity in AlexWortega/universal-nla-v24-dirfix about 2 months ago

correct to a working Github link

#1 opened about 2 months ago by

New activity in JetBrains/Mellum2-12B-A2.5B-Thinking 4 months ago

Vllm usage guide

#6 opened 4 months ago by

New activity in AlexWortega/pi-agent 4 months ago

suggestions

#1 opened 4 months ago by

New activity in webml-community/bonsai-image-webgpu 4 months ago

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

#6 opened 4 months ago by

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

#17 opened 4 months ago by

New activity in AlexWortega/qwen35-4b-soyuz-merged-gguf 4 months ago

Create README.md

#1 opened 4 months ago by

New activity in naitik12kumar/qwen-kalkulio-lora-14b-v4 4 months ago

Update README.md

#1 opened 4 months ago by

commented 2 papers 9 months ago

MMFormalizer: Multimodal Autoformalization in the Wild

Paper • 2601.03017 • Published Jan 6 • 49 •

MMFormalizer: Multimodal Autoformalization in the Wild

Paper • 2601.03017 • Published Jan 6 • 49 •

New activity in Goodfire/DeepSeek-R1-SAE-l37 10 months ago

Expansion factor same on logic vs. math?

#2 opened 10 months ago by

New activity in transcendingvictor/delphi-llama2-100k-validation-logits 10 months ago

seems logits

#2 opened 10 months ago by

New activity in deepseek-ai/DeepSeek-V3.2-Exp 10 months ago

The whale is back

#8 opened 12 months ago by

New activity in LiquidAI/LFM2-ColBERT 11 months ago

Scores

#1 opened 11 months ago by

commented a paper 12 months ago

RLP: Reinforcement as a Pretraining Objective

Paper • 2510.01265 • Published Sep 26, 2025 • 47 •

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

Any plans for a Qwen3-32B model?

#9 opened over 1 year ago by

commented a paper over 1 year ago

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

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

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

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

#28 opened over 1 year ago by

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

Synthetic Data Collection PAUSED Jan 16

#21 opened over 1 year ago by

New activity in Qwen/QwQ-32B-Preview almost 2 years ago

QuietSTAR?

#9 opened almost 2 years ago by

albatrossbirdie