Bounded Regret

Cross-posted from the Transluce blog.

Technically skilled people who care about AI going well often ask me: how should I spend my time if I think AI governance is important?

Currently, we primarily oversee AI with human supervision and human-run experiments, possibly augmented by off-the-shelf AI assistants like ChatGPT or Claude.

This is a brief overview of a recent release by Transluce.

We are launching an independent research lab that builds open, scalable technology for understanding AI systems and steering them in the public interest.

This is a guest post by my student Ruiqi Zhong, who has some very exciting work defining new families of statistical models that can take natural language explanations as parameters.

To communicate risks, we often turn to stories.

This is a landing page for various posts I’ve written, and plan to write, about forecasting future developments in AI.

I previously discussed the capabilities we might expect from future AI systems, illustrated through GPT2030, a hypothetical successor of GPT-4 trained in 2030.

Given their advanced capabilities, future AI systems could pose significant risks to society.

I'm experimenting with hosting guest posts on this blog, as a way to represent additional viewpoints and especially to highlight ideas from researchers who do not already have a platform.

Two years ago, I commissioned forecasts for state-of-the-art performance on several popular ML benchmarks.

GPT-4 surprised many people with its abilities at coding, creative brainstorming, letter-writing, and other skills.

The deployment of powerful deep learning systems such as ChatGPT raises the question of how to make these systems safe and consistently aligned with human intent.

Note: This post is based on a Google document I created for my research group.