AI Safety Research

AISafety

·

https://humanaligned.ai

AI & ML interests

LLMs, planning, EA

Recent Activity

liked a model about 13 hours ago

Nanbeige/Nanbeige4.2-3B

liked a model about 13 hours ago

moonshotai/Kimi-K3

commentedon an article 4 days ago

Security incident disclosure — July 2026

View all activity

Organizations

upvoted an article 7 days ago

Article

Security incident disclosure — July 2026

system

•

13 days ago

• 704

upvoted a paper 7 days ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published 21 days ago • 138

upvoted a paper 8 days ago

Loop the Loopies!

Paper • 2607.16051 • Published 12 days ago • 73

upvoted a collection 14 days ago

NLA Models

Natural Language Autoencoders across Llama, Gemma, and Qwen. Code: https://github.com/kitft/natural_language_autoencoders/ • 8 items • Updated May 6 • 17

upvoted a collection 18 days ago

NVFP4

Dynamic Unsloth NVFP4 Quants. Faster and more accurate. • 10 items • Updated 11 days ago • 49

upvoted a paper about 1 month ago

S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence

Paper • 2606.20515 • Published Jun 18 • 41

upvoted 3 collections about 2 months ago

PP-OCRv6

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 19 items • Updated Jun 15 • 106

DeepSeek-V4

6 items • Updated Jun 27 • 759

Ideogram 4

8 items • Updated Jun 4 • 67

upvoted a collection 2 months ago

Bonsai Image

6 items • Updated Jun 4 • 93

upvoted a paper 2 months ago

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published May 14 • 91

upvoted 2 collections 3 months ago

Step-3.5-Flash

step 3.5 models • 9 items • Updated Mar 14 • 40

Qwen-Scope

16 items • Updated May 14 • 76

upvoted 2 collections 4 months ago

ShareGPT Datasets

22 items • Updated Mar 2 • 17

Mistral Small 4

A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated Mar 16 • 76

upvoted 3 articles 7 months ago

Article

Exploring Environments Hub: Your Language Model needs better (open) environments to learn

anakin87

•

Sep 4, 2025

• 32

Article

HUMAINE: A Rigorous Framework for Understanding AI Through Human Experience

ProlificAI

•

Sep 16, 2025

• 7

Article

From GRPO to DAPO and GSPO: What, Why, and How

NormalUhr

•

Aug 9, 2025

• 133

upvoted a collection 8 months ago

Olmo 3

Artifacts for the Olmo 3 release. • 7 items • Updated Mar 2 • 174

upvoted an article 8 months ago

Article

We Got Claude to Fine-Tune an Open Source LLM

burtenshaw, evalstate

•

Dec 4, 2025

• 631