But what's the point of re-building "standard software" if it is so standard that it already exists 100 times in the training data with slight variations?
Very cool book. I think a reason why ML has seen so much progress despite benchmark overfitting/abuse is that results are "regularized" by real world applications and the Lindy effect. Methods, or research, that abuse benchmarks aren't adopted by follow-up research so they tend not to survive. And they aren't adopted because people try them but then find out that they don't generalize to other/newer benchmarks. So the system works not because of specific benchmarks, but because of how the community as a whole deals with benchmarks.
Competitiveness doesn't really come from architecture, but from scale, data, and fine-tuning data. There has been little innovation in architecture over the last few years, and most innovations are for the purpose of making it more efficient to run training or inference (fit in more data), not "fundamentally smarter"
I think your last point is the important one. I don't mind vibe coded app if they are polished. But a polished vibe coded app looks like a non-vibe-coded app because of the polishing. The polishing is 95% of the effort. This app here looks fully vibe coded, without much polishing, at least to me.
A bit off-topic, but it's interesting how the first thing I check now is whether this is a vibe coded app (which it seems to be) or something that had serious effort put into it.
I don't think your Github example is accurate. The vast majority of developers started using git after Github became a thing. They may have used svn or another type of collaboration system before, but not git. And the main reason they started using git is because Github was such massive value on top of git, not because git was so amazing.
But can't you do the same using appropriate MCP servers with any of the LLM providers? Even just a generic browser MCP is probably enough to do most of these things. And ChatGPT has Tasks that are also proactive/scheduled. Not sure if Claude has something similar.
If all you want to do is schedule a task there are much easier solutions, like a few lines of python, instead of installing something so heavy in a vm that comes with a whole bunch of security nightmares?
Okay, but most of the time you can't prompt your AI to successfully debug you out of problems if you don't understand code. Or when you do the AI will solve the problem in a way that creates a dozen more cascading problems an hour later. I've also been coding for 20 years now and I feel like my coding skills are just as important now as they were 10 years ago. Without them I'd never be able to use AI effectively.
The only exception really are greenfield apps like "create a toy todo app demo" or "scaffold this react project" but that's like 0.001% of real world engineering work.
Captcha is a completely useless system trivially solved by many agents and services. The only thing captcha does is annoy humans. I do agree with the problem, but I don't know what a solution would look like outside of government identification.
In the six years you are using your computer, do you ever expect to run into versioning issues and conflicts? Homebrew packages conflicting with local packages, something you compile give needs a different python/ruby/node/rust/whatever version that you have locally installed, you want to quickly try out a new package or upgrade without changing your system but have the option of rolling back safely, need to quickly install a database, want to try out a new shell and shell config but don't brick your system and have the option to roll back, etc. Nix gives you all of that and more for a one-time setup cost. Your argument is correct only if you expect to never change anything on your computer for the 6 years. But if I think about how often I have fought with homebrew or some kind of versioning/path/binary conflicts in the past then the investment in nix has paid off exponentially.
It's also about peace of mind like you said. Before nix I sometimes felt anxiety installing or upgrading certain things on my computer. "Will this upgrade break stuff?" - and often it did and I'd have to spend the next few hours debugging. With nix I don't worry about any of that anymore.
I think what it comes down to, and where many people get confused, is separating the technology itself from how we use it. The technology itself is incredible for learning new skills, but at the same time it incentivizes people to not learn. Just because you have an LLM doesn't mean you can skip the hard parts of doing textbook exercises and thinking hard about what you are learning. It's a bit similar to passively watching youtube videos. You'd think that having all these amazing university lectures available on youtube makes people learn much faster, but in reality in makes people lazy because they believe they can passively sit there, watch a video, do nothing else, and expect that to replace a classroom education. That's not how humans learn. But it's not because youtube videos or LLMs are bad learning tools, it's because people use them as mental shortcut where they shouldn't.
You absolutely need to spend money in PoE to buy stash tabs. It's basically mandatory if you play regularly. The difference to most dark patterns is that the spending has a very low cap. Once you've spent $50 or so on stash tabs you are set forever and never need to spend again. So it's not so different from buying a $50 game, just that you get to try it out for free first.
I don't really see how examples are useful because you're not going to understand the context. My prompt may be something like "We recently added a new transcription backend api (see recent git commits), integrate it into the service worker. Before implementing, create a detailed plan, ask clarifying questions, and ask for approval before writing code"
It doesn't feel off to me because that's the exact experience I've had as well. So it's unsurprising to me that many other people share that experience. I'm sure there is a bunch of paid promotion going on for all kinds of stuff on HN (especially what gets onto the front page), but I don't think this is one of those cases.
Interesting, my experience has been the opposite. I've been running Codex and Sonnet 4.5 side by side the past few weeks, and Codex gives me better results 90% of the time, pretty much across all tasks. Where Claude really shines is that it's much faster than codex. So if I know exactly what I want or if it's a simpler task I feel comfortable giving it to Claude because I don't want to wait for Codex to work through it. Claude cli is also a much better user experience than codex cli. But Codex gets complex things right more consistently.
Yeah, reading the docs it seems you are right. The landing page mentions AI-native at the very top and all over the place, so I got the wrong impression that it's somehow tightly coupled to an AI integration. But looks like it's optional.