Bret Taylor: recommendation

Transcript context

…Turning your life into code? Yeah, it's like you almost want to put everything in a file system that looks like source code, not because that's the only way these agents can work, but actually it's quite an efficient way to get a mix of context and random access memory. If you think about a vector database, it's more random access. You have to know what to look for. But actually, that's not how real memory works. There's a mix of it. You're loading a markdown file, and as you said, compaction, all these things matter. But the messiness of it actually probably produces a more useful agent than a lot of the fancier things. I use memory in ChatGPT, and I love it. But I actually think this idea that there's a directory of just everything you've ever done is actually maybe more useful to an AI than people think. Actually, if you follow over the past couple of months, just this emergence of harness engineering, where you're building the harness around an agent to do work, I wonder if in the short term, it might just be one of those idiosyncrasies of history, like mimicking a code base is actually the best way to make a general-purpose agent work. Maybe over time, we'll get fancier than that, but it's actually a relatively efficient harness for an agent. Anyway, maybe that's why it's— It's very terminal-centric. It's backwards compatible with—…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.