Blog
Insights & Research
Research, analysis, and insights from Forum AI on expert-driven AI evaluation, benchmarking methodologies, and the future of trustworthy AI systems.
How We Turn Expert Insight Into Action
From expert interviews to AI judges
Matt Wilde
Speed-Running Content Moderation
What fifteen years of social media safety teaches about evaluating AI
Matt Wilde
How We Pick the Right Experts to Evaluate AI
Four principles that guide our work
Ranjit Bhatia
We're Teaching AI to Think Like World-Class Experts
Here's how
Andy Hall
How to Train AI to Tell the Truth About Politics
Ideological bias and beyond
Andy Hall
Not All Queries Are Created Equal
Engineering a classification system for LLM evaluation
Sarah Young
Will AI Replace My Job?
A view from the front lines of AI development
Robbie Goldfarb
AI Companies Can’t Grade Their Own Homework
We're heading toward our own meatpacking moment
Kathryn Salam
Toward wiser machines
Three capabilities should govern the future of AI
Robbie GoldfarbWhy We Built Forum AI
How do we ensure AI systems are accurate and trustworthy when they're becoming the primary way millions of people get information?
Campbell Brown, Robbie GoldfarbWhen AI Needs Judgment, Not Just Data
AI has conquered technical and creative challenges remarkably well.
Robbie GoldfarbThe Disappearing Expert
There was a book published in 2017 called “The Death of Expertise” that explained why so many of us turned against established experts.
Campbell BrownExpert-in-the-Loop
As AI grows more sophisticated, we need more sophisticated data to improve it.
Robbie GoldfarbNo-Bias, No-Bull AI
I've spent my career grappling with bias.
Campbell Brown