Menu
Sign In Search Podcasts Libraries Charts People & Topics Add Podcast API Blog Pricing

Rob Wiblin

πŸ‘€ Speaker
3881 total appearances
Voice ID

Voice Profile Active

This person's voice can be automatically recognized across podcast episodes using AI voice matching.

Voice samples: 1
Confidence: Medium

Appearances Over Time

Podcast Appearances

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

Face masks, yeah.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

Oh God, okay, yeah.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

So to sum up the picture as I vaguely see it, there's a whole lot of things that we can do to try to improve refusal behavior that I imagine with a big push, we could maybe become, the closed source models like Claude could become quite robust against jailbreaks, quite unwilling to help with obvious production of bioweapons.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

There we've got a challenge that it might be difficult to get all of the frontier models to have it because we're currently seeing like some companies compete on safety, some companies compete on speed and not having safety.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

That's like what they almost view as their comparative advantage.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

And so you could just have like, if you have like one model that is incredibly capable that has almost no refusal behavior, then well, it doesn't, you haven't helped all that much.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

But setting aside the closed source models where maybe we could pull that off,

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

With the open source models, it's going to be possible always basically to fine tune them to get over any of this like reluctance that they have to help.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

So then the question is like, you have to make them incapable of helping.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

And what can we do there?

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

I suppose we could try to take the knowledge out of the training data so that it's not that they know how to do virology, but they have been told not to do it, is that they simply couldn't help you even if they wanted to.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

But there you've got to challenge that the data that you would use to teach them virology probably is public, probably could be harvested off of the internet to a great extent.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

And so someone could try to add that knowledge back in to an open source model just before they used it.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

Do I understand the broad picture right?

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

Well, like more hopefully distillation.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

So you train a new model that's like a smaller version of the other one, but you make sure that none of the information that goes from the original one to the second one includes anything about biology or virology.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

Okay, so access controls have their place.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

They're quite useful, potentially.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

They can buy us some time.

80,000 Hours Podcast
AI designs genomes from scratch & outperforms virologists at lab work. What could go wrong? | Dr Richard Moulange, CLTR

They can buy us some risk reduction guardrails.