f0e4c2f7

All these security issues have made me want to build more of my own slimmed down tools. It would be great if there were better ways to use claude code with my own minimal harness and still have access to the pro plan.

> Since 2023, everything learned in Year X was 99% useless in year X+1.

Personally I disagree with this. I've been using LLMs the last few years and learning a lot about techniques for getting value out of them. Even though they weren't very good for a while they seemed worth learning to me because the rate of improvement was so fast. We've now reached a point where if you know how to use them right you can get lots of value out of them.

I really don't mean to be rude here but consider perhaps the reason why you're having trouble seeing why they're valuable is because you haven't used them enough in the last few years or kept up with the developments closely enough. Maybe I'm wrong. But consider it's possible you are too.

> This has also been said every other month since 2023.

I'm sure others have said that but my perspective has been that the models are not quite good enough yet, for a while but that the trajectory is so crazy that it made sense to make the bet and invest lots of time into learning how to use them on the assumption that they would soon be good.

Even now I would say they have a long way to go. What is hard but possible today will be easy tomorrow. But quite a lot is now possible with the right techniques. Crazy things.

The tools have a learning curve. You can get extreme amounts of value out of them but you have to learn how to use them. Many tools are this way.

It might make sense to learn now, before everyone expects that you be an expert with this tool in order to do your job. On the other hand perhaps they will be easier to learn if you wait.

There is an incredible amount of nuance to be had in using LLMs and we reached the stage, probably only in the last few weeks where all the pieces have fallen into place such that if you are skilled at using the LLMs just about all of the previous problems with them can now be easily mitigated. If you learn how. There is a lot to learn.

This is actually the typical case when new projects drop on HN. Dropbox is the canonical example.

You gotta not take it personal. Announcing on HN is a gauntlet. People can be a bit prickly. Just a bit though. You get lots of good feedback too.

It's amusing to me this entire article is centered around brow beating this and other hypothetical software authors for starting things without doing a small amount of research first to understand the very basics of what they're getting into.

If the author of the article had done just a small amount of research about bend or it's author before writing the article they would have known pretty quickly what they were saying was incorrect.

I think the larger pattern here is that nuance is one of the most valuable commodities in the AI era. If you're hand waving stuff away without even missing , you're going to miss a lot of stuff in this cycle.

This article reminds me a lot of the famous hacker news Dropbox comment.

Very interesting. So how open is the neural band to hack on? Do you expect this to be something to get patched out eventually if you update? Seems like a really cool platform to develop against outside of the intended ecosystem.

Ahhhh yeah totally get that. Changes things considerably.

Have you considered setting up an agent environment like codex and having it work making on Android version for you? I know you said it's a very complex app and that probably makes it seem like it wouldn't be able to, but LLMs are really good when they have a very clearly defined end state to work toward, like an existing iOS app with code, screenshots etc.

I bet if you set Astra codex against this task on the $100 plan it would have it done at a speed that would shock you. Potentially even by the end of the day and mostly uninterrupted.

The SOTA models can reverse engineer whole codebases even from assembly now. If you have to specify with words what you want to do it's still hard but if you have a codebase to work from, you can pretty much arbitrarily convert apps and games into other languages / platforms now as if by transitive property.

I related a lot to the feelings in this article but over the past year I've come to a different conclusion than the author. In the end of the article he says that there are 3 paths available to him, but I believe there is an additional path to consider.

You can use the AI tools but still program by hand every day for practice and fun. Programming becomes deliberate practice to keep your skills and mind sharp. Like going to the gym, but for your brain. You can use the LLMs to push and challenge yourself, setting more aggressive and ambitious goals than you might have in the old days for learning.

I used to think of software dev like climbing a mountain. Hard, and I loved it. I loved it because of the difficulty. That was the most fun part. Getting to the top, the summit. That was incidental to me. I wouldn't even defend that as a good thing. Certainly not good engineering. It was just what I liked. Any good engineering was incidental to how fun the hard parts of the puzzle were.

Then LLMs came along and I thought "this is like a helicopter. You can go straight up to the top in a few minutes." While very practical, it also led to the feelings the author described. After months of handwringing and using the tools, having existential crises - I've arrived at a new conclusion:

It's not a helicopter. It's a jetpack. And it's still hard to use if you push it to it's absolute limit. Knowing just the right spot to grab the rock as you fly by. Taking as much risk as possible, but not too much. Pushing both the jet pack (or perhaps it's an iron man suit now with latest models) and the rock climbing knowledge as far as they will go. Screwing up, falling off the wall, and learning.

And with this jetpack you can get to places you never could have climbed to without it. Not just the top. Weird, interesting spots on the mountain.

That perspective, which I've taken to over the last month or two has helped me find the fun again. The existential crises have ended and I'm back to feeling about software dev the way I felt a few years ago. Boundless joy and excitement. Probably more now.

This feels like satire / parody. Praising LinkedIn. The text itself containing multiple LLM tells, especially in the parts complaining most about LLM writing.

Maybe not. Could just be kind of accidentally ironic with the author picking up LLM quirks from using them a lot.

Funny in either case.

I read this whole thing a couple days ago. Really long but super interesting. Worth reading imo.

A lot of handwringing about the security implications but I think the accomplishments of the swarm itself are the most interesting. Next rung up on the ladder of abstraction I suspect.