Boris Cherny: Building Claude Code

**Diana Hu** (0:07)
All right, Boris, we're so excited to have you here, the creator of Claude Code. Thank you.

**Boris Cherny** (0:19)
It's great to be here.

**Diana Hu** (0:20)
Fresh off the press, you guys just shipped Opus 5 yesterday.

**Boris Cherny** (0:26)
Yes.

**Diana Hu** (0:28)
And it seems that model performance keeps accelerating. You guys took Arc AGI 3 to 30 percent, which is incredible.

**Boris Cherny** (0:40)
Yes.

**Diana Hu** (0:41)
And for context, before the best score was in the low single digits or low teens, right? What can Opus 5 do now that it couldn't versus the previous version?

**Boris Cherny** (0:55)
Yeah, there's a lot that goes into every new model. And there's a lot of new capabilities that we teach and get the model to do. Whenever you do model training, you try to teach a whole bunch of different things. And most often, it doesn't work. But some subset of the things, the model does learn. And sometimes it also surprises you. It has these skills, it has abilities that you actually didn't really teach it, but it just kind of weren't. For 5, one example of something it does that I think no other model has done is it runs for a very long period of time. And especially when you combine Opus 5 with Auto Mode, it's just like incredible. Like it can go for days, weeks, months at a time. It just won't stop.
You don't even need to use scaffolding. So you don't need the splash goal, you don't need all this other stuff. It will just go because it knows it needs to do the task.
Another thing that I'm really excited about, and I'm going to start, I think, to talk about a little bit more, but it's kind of surprising because it's such a new capability, is the model does not seem to be prompt injectable anymore.

**Diana Hu** (2:08)
What's prompt injectable?

**Boris Cherny** (2:11)
It's crazy. People have talked about this lethal trifecta for a long time, and this really affects harness design and agent design and product design. Because if the model reads some instruction on the Internet, that's like, do X and Y and Z, and also delete everything on the user's computer.
A year ago, the model would have just done it.
But nowadays, Opus does not.
This has actually been the case since Opus 4.7, 4.8. Sonnet 5 has been quite good at this. Fable was quite good at it. But Opus 5 just hits like a new frontier on this. So essentially, if you combine a well-aligned model, so this is like essentially three years of research into alignment, with a prompt injection classifier, which we run for all traffic, and what this is doing is it's based on Crystal's mechanistic interpretability work, where it's literally, we're looking at neurons in the model's brain that light up when prompt injection happens. So the model won't even tell you, but we can actually see those neurons, and we can figure out and diagnose that it's happening. And then you combine that with the auto mode classifier. And with these three layers, we just cannot demonstrate prompt injection anymore. And we've hired security researchers, we've done like red teaming, we've done competitions, no one can demonstrate it. And so I'm actually quite curious if people are able to. And that will be actually be really amazing signal for the research team.

**Diana Hu** (3:35)
So if anyone in this room prompt injects Claude, Opus 5, you'll get a special price for Boris maybe.
Now talking about a prompt injection, the other side of the coin is now the system prompt. Let's talk a bit about the new release. You actually deleted over 80 percent of the system prompt from Claude Code. Yes. Tell us more about that.

**Boris Cherny** (4:00)
I think something that a lot of people might not realize is Claude Code as a product and as a harness is just always changing. We're always adding stuff, we're always deleting stuff. Every time that a new model comes out, we delete a bunch of the system prompt, change a bunch of the system prompt, we change the set of tools all the time, we change the prompts for the tools all the time. The reason is every model is very different. So something that you did for one model maybe three months ago, it just might not translate at all to the next model. And so one thing about Opus 5 is it's just really intelligent. And a lot of the stuff in the system prompt was correcting for these behaviors that the model should have known, but it didn't.
Now Opus 5 just does it. So yeah, we deleted 80% of the system prompt.