AI Safety Research

AISafety

·

https://humanaligned.ai

AI & ML interests

LLMs, planning, EA

Recent Activity

upvoted a paper about 15 hours ago

Loop the Loopies!

liked a dataset 5 days ago

Soofi-Project/SOOFI-S-Base-eval-scores

liked a model 7 days ago

extraltodeus/Qwen3.5-9B-Nikusui-v1

View all activity

Organizations

upvoted a paper about 15 hours ago

Loop the Loopies!

Paper • 2607.16051 • Published 5 days ago • 63

upvoted a collection 7 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 11 days ago

NVFP4

Dynamic Unsloth NVFP4 Quants. Faster and more accurate. • 10 items • Updated 4 days ago • 46

upvoted a paper 29 days ago

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

Paper • 2606.20515 • Published Jun 18 • 40

upvoted a collection about 1 month ago

PP-OCRv6

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 19 items • Updated Jun 15 • 104

upvoted 3 collections about 2 months ago

DeepSeek-V4

6 items • Updated 25 days ago • 750

Ideogram 4

8 items • Updated Jun 4 • 67

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 • 75

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 • 75

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

• 129

upvoted a collection 7 months ago

Olmo 3

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

upvoted an article 7 months ago

Article

We Got Claude to Fine-Tune an Open Source LLM

burtenshaw, evalstate

•

Dec 4, 2025

• 630

upvoted a collection 8 months ago

Transformers.js demos

A collection of my favorite WebML demos, built with Transformers.js! • 30 items • Updated Jun 17 • 146

upvoted a paper 8 months ago

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

Paper • 2511.22570 • Published Nov 27, 2025 • 96