Sashank Pisupati

spisupat

reflectionai

·

https://spisupat.github.io/

AI & ML interests

Alignment & safety, failure modes of intelligence, RL

Recent Activity

upvoted an article about 1 month ago

Featuring Every Eval Ever Results on Hugging Face Model Pages

authored a paper about 2 months ago

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

upvoted a paper about 2 months ago

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

View all activity

Organizations

liked a Space 9 months ago

The Smol Training Playbook

The secrets to building world-class LLMs

liked a model 10 months ago

milli19/promptmii-llama-3.1-8b-instruct

8B • Updated Oct 1, 2025 • 6 • 4

liked 2 models about 1 year ago

AtlaAI/Selene-1-Llama-3.3-70B

Text Generation • 71B • Updated Jul 25, 2025 • 42 • 8

AtlaAI/Selene-1-Llama-3.3-70B-GPTQ-W8A8

Text Generation • 71B • Updated Jul 25, 2025 • 20 • 2

liked a model over 1 year ago

AtlaAI/Selene-1-Mini-Llama-3.1-8B

Text Generation • 8B • Updated Jul 25, 2025 • 2.68k • • 107

liked a model almost 2 years ago

DefamationStation/Artificium-llama3.1-8B-001-Q8_0-GGUF

8B • Updated Sep 9, 2024 • 11 • 2