Alex Shan's videos and podcasts

They rly did it https://t.co/0XR7pdT5Ys

This is why you need agentic judges that ingest th...

This generalizes outside of foundation model evals. Every agent engineering team needs to understand their agent's behavior in its most common tasks.

we are still so early

sorry, that's only available in our enterprise pla...

+1. @stanfordnlp has a rich background in interpre...

Roger Federer will soon be a brand ambassador and ...

it's the little things in life https://t.co/YTsCgc...

having infra that can support the types of increas...

Between @harvey and @cognition 's raise posts, the...

sooo https://t.co/ZJ9xig6L9e https://t.co/evjNE7PI...

American tennis is so back 🇺🇸

Ramp at $60B, yum yum just spin out the model lab...

A year ago, I made this viral post about DeepMind believing they were close to solving one of the mi...