The 80,000 Hours Podcast on Artificial Intelligence

← The 80,000 Hours Podcast on Artificial Intelligence5 jun · 3 u 03 min

Nine: Neel Nanda on the race to read AI minds

Nine: Neel Nanda on the race to read AI minds5 jun3 u 03 min

Nobody knows how AIs think, or why they do what they do.

Or at least, we don’t know much. Not the companies building them, the researchers studying them, or the governments beginning to rely on them.

This is only becoming more troubling as AIs grow more capable and appear on track to wield enormous cultural influence, directly advise on major government decisions, and even operate military equipment autonomously. We simply can’t tell what models, if any, should be trusted with such authority.

Neel Nanda of Google DeepMind is one of the founders of mechanistic interpretability — the field of trying to give us insight into what’s happening inside AI models.

The project has generated enormous hype, exploding from a handful of researchers five years ago to hundreds today — all working to make sense of the jumble of tens of thousands of numbers that frontier AIs use to process information and decide what to say or do.

But Neel now has a warning for us: the most ambitious vision of mechanistic interpretability is probably dead. He doesn’t see a path to deeply and reliably understanding what AIs are thinking. The technical and practical barriers are too great to get us there before competitive pressures push us to deploy human-level or superhuman AIs.

Neel argues no single approach will guarantee safe alignment, and our only choice is the 'Swiss cheese' model of protection: layering multiple safeguards on top of one another.

That doesn’t mean mechanistic interpretability has failed. It won’t be a silver bullet for AI safety, but it will be one of the best tools in our arsenal.

For example, by inspecting the neural activations in the middle of an AI’s thoughts, we can see many of the concepts the model is thinking about — from refusing to answer a question, to the option of deceiving the user.

We can’t track every thought a model is having at every moment, but catching 90% of the concepts it uses 90% of the time should help us muddle through — as long as mechanistic interpretability is paired with other techniques to fill the gaps.

In this episode, Neel takes us on a tour of the race to understand what AIs are really thinking. He and host Rob Wiblin cover:

The best tools we’ve come up with so far, and where mechanistic interpretability has failedWhy the best techniques have to be fast and cheapThe fundamental reasons we can’t reliably know what AIs are thinking, despite having perfect internal access to themWhat we can and can’t learn by reading models’ ‘chains