18 korrents from this recording
Every claim below is a statement made in this recording, quoted word for word and linked to the second it was said, so you can hear it rather than take our word for it. The wording comes from the transcript published alongside the recording; the sentence above each quote is our reading of the claim, not their wording.
Their wordsit turns out you can do this if you think really hard about okay, how do I have agents prove to me that the stuff they've written works?
Their wordsI think Opus 4.5 was the first one that earned my trust. Like I'm very confident now that for classes of problems that I've seen it tackle before, it's not going to do anything stupid.
Their wordsthe key thing about TDD is that it means that the agents won't write more than they need to.
Their wordsI think I see people who are writing code with coding agents and they're not writing any tests at all. That's a terrible idea.
Their wordsjust cuz the test suite passes doesn't mean that the web server will boot. You know, there's there's always a chance that when you actually try in the real world, something's not going to work.
Their wordsAnd what you can do if you've got one of these conformance suites is you can give it to a a good agent and say, "Write code until this test suite passes." And it kind of will.
Their wordsAnything that you're maintaining over the longer term, the code quality does start really really mattering.
Their wordsone of the magic tricks about these things is that they they're incredibly consistent. If you've got a code base with a bunch of patterns in, they will follow those patterns almost to a T.
Their wordsThe problem with language models is they're incredibly gullible by design. Like, language models do exactly what you tell them to do, and they will believe almost anything that you say to them.
Their wordsProblem is, you can solve SQL injection by parameterizing your queries. You can't do that with LLMs.
Their wordsI call it the lethal trifecta because the only guaranteed solution is to cut off one of the legs.
Their wordsSo, I think the most important thing is sandboxing. You want your coding agent running in an environment where if something goes completely wrong, if somebody gets malicious instructions to it, that the damage is greatly limited.
Their wordsOpenAI and Anthropic have both realized that code is the most important thing to optimize the models for, cuz that's where the money is. Like coders will spend $200 a month on a plan if it's good enough, it turns out.
Their wordsI think the most interesting question is what can the models we have do right now? And so the only thing I care about today is what can Claude Opus 4.6 do that we haven't figured out yet. And I think it will take us 6 months to even start exploring the boundaries of that.
Their wordsI think that might be what saves us. I think the fact that no, you can't have one engineer and have him do a thousand projects because after three hours of that he's going to literally pass out in a corner.
Their wordsif you've always stuck to two programming languages because of the overhead of learning a third, go and learn a third right now. And don't learn it, just start writing code in it.
Their wordsWhy would I use a date picker library where I'd have to customize it when I could have Claude write me the exact date picker that I want.
Their wordsprojects are flooded with junk contributions at the moment to the point that people are trying to convince GitHub to disable pull requests, which is something GitHub have never done.