推文

We've gone really quickly from "local models are dogshit" to "local models are good actually" (like, a 12 month window from A to B). I don't think they're actually good ENOUGH yet. We need an Opus 4.5 quality local model. When that happens, I think the world will spill over. Opus 4.5 is/was amazing, and is more than good enough for almost all tasks still as long as you pair with a frontier-level planner/judge. It'll still require a hugely expensive machine to run it, I'm sure, like a $5K or more laptop or mac studio. But, that's going to be pennies compared to the API costs plus all the benefits of guaranteed privacy and so on.

This is why PR diff speed matters. This isn't a dunk on GitHub specifically, because GitLab, Forgejo, etc. are all equal or worse. But this is the kind of thing that drives me nuts, because this is a core workflow and its slow enough I literally take my hands off the keyboard. Btw, when my mouse jiggles on the left, its because the page is literally skipping frames and I'm instinctively shaking my mouse to see if it'll respond. And on the keyboard input you can literally here me finish typing before a letter even shows up. For someone like me who is an expert at these tools, my brain navigates the tool dramatically faster than it can keep up, and that is not good. The tool should not get in the way.

AI slop is good, actually. Slop is what enables fast parallel experimentation. The etiquette and skill is understanding the boundaries of where slop exists and the extent to which it should be cleaned up and how. A few examples: I’m working on the internals of some system right now. The API and GUI of this thing is fully zero shame slop. It’s horrible. But it lets me focus on the core quality while shipping a usable piece of alpha quality software to testers (transparent about the slop frontend). Similarly, this system has plugins. We sent agents in Ralph loops overnight to generate dozens of plugins. The plugins are slop. The quality is bad. The plugin API/SDK is absolutely not done. But we can test a full GUI with a full plugin ecosystem. When we change the API, we can regenerate them all. The cost of change is just tokens, the velocity is incomparable to before. I built Terraform. We tested and shipped TF 0.1 with about 3 very weak providers. Because we ran out of time. Building was slow. And when we changed our SDK the cost was immense. Totally different today, 10 years later. Today, I would’ve slop generated 100 providers (again, with transparency and cleanup later, but just to prove it out). As an anti example, I would not PR this (without prior warning) to another project. I would not throw this onto customers without full review or transparency (as I’m already doing). I would not accept first pass slop. It’s almost never right. Slop is a tool. And like anything else it’s not blanket bad or good. The context is everything.