News Source

The Shift from Models to Compound AI Systems

AI caught everyone’s attention in 2023 with Large Language Mode...

Ghostbuster: Detecting Text Ghostwritten by Large Langu...

The structure of Ghostbuster, our new state-of-the-art metho...

Asymmetric Certified Robustness via Feature-Convex Neur...

Asymmetric Certified Robustness via Feature-Convex Neural Networks ...

TinyAgent: Function Calling at the Edge

The ability of LLMs to execute commands through plain langu...

Modeling Extremely Large Images with xT

As computer vision researchers, we believe that every pixel can...

2024 BAIR Graduate Directory

Every year, the Berkeley Artificial Intelligence Research (BAIR) La...

Linguistic Bias in ChatGPT: Language Models Reinforce D...

Sample language model responses to different varieties of En...

How to Evaluate Jailbreak Methods: A Case Study with th...

When we began studying jailbreak evaluations, we found a fascin...

Are We Ready for Multi-Image Reasoning? Launching VHs: ...

Humans excel at processing vast arrays of visual information, a...

Virtual Personas for Language Models via an Anthology o...

We introduce Anthology, a method for conditioning LLMs to r...

September 2024 Newsletter

MIRI updates Aaron Scher and Joe Collman have joined the Technical Governance Te...

October 2024 newsletter

News and links Geoffrey Hinton and John Hopfield were awarded this year’s Nobel ...

MIRI’s 2024 End-of-Year Update

MIRI is a nonprofit research organization with a mission of addressing the most ...

Communications in Hard Mode

Six months ago, I was a high school English teacher. I wasn’t looking to change ...

The Sun is big, but superintelligences will not spare E...

Crossposted from Twitter with Eliezer’s permission i. A common claim among e/acc...

MIRI Newsletter #121

MIRI updates Eliezer Yudkowsky joined Stephen Wolfram on the Machine Learning St...

This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies.