561–570 of 918 posts
Earlier quoted context omitted.
AI can help with that too by automatically fixing bugs.
I find it such a strange cycle to tell AI to write some code, then tell it to fix the bugs in that code. Why didn't the AI just not include those bugs the first time it wrote the code ?!
I started programming over 40 years ago because it felt like computers were magic. They feel more magic today than ever before. We're literally living in the 1980s fantasy where you could talk to your computer and it had a personality. I can't believe it's actually happening, and I've never had more fun computing. I can't empathize with the complaint that we've "lost something" at all. We're on the precipice of somet…
> I can't empathize with the complaint that we've "lost something" at all. We could easily approach a state of affairs where most of what you see online is AI and almost every "person" you interact with is fake. It's hard to see how someone who supposedly remembers computing in the 80s, when the power of USENET and BBSs to facilitate long-distance, or even international, communication and foster personal relationship…
Earlier quoted context omitted.
But it write mostly useless documentation Which take time to read and decipher. And worse, if you are using it for public documentation, sometimes it hallucinate endpoints (i don't want to say too much here, but it happened recently to a quite used B2B SaaS).
Loop it. Use another agent (from a different company helps) to review the code and documentation and call out any inconsistencies. I run a bunch of jobs weekly to review docs for inconsistencies and write a plan to fix. It still needs humans in the loop if the agents don’t converge after a few turns, but it’s largely automatic (I baby sat it for a few months validating each change).
- “You’re not spending enough money”
- “You’re not micromanaging enough”
Seriously?
Earlier quoted context omitted.
There are many tens (hundreds?) of billions of dollars being poured into the smartest minds in the world to push this thing forward I'm not so confident that it'll only be code monkeys for too long
Until they can magically increase context length to such a size that can conveniently fit the whole codebase, we're safe. It seems like the billions so far mostly go to talk of LLMs replacing every office worker, rather than any action to that effect. LLMs still have major (and dangerous) limitations that make this unlikely.
Earlier quoted context omitted.
And yet.. my car was surrounded by 5 self-driving cars with no people in them on the way to work on Thursday.
And your ability to go your own way is only temporary and due to inertia. Today, for a while, you can still buy a vehicle that requires a driver and doesn't look and perform exactly like every other waymo. But that's only because self driving cars are still new and incomplete. It's still the transition period. I already can't buy the car I want with a manual transmission. There are still a few cars that I could get w…
Don’t panic, it’s only one additional subscription away. /s
Earlier quoted context omitted.
I love programming, but most of that joy doesn't come from the type of programming I get paid to do. I now have more time and energy for the fun type, and I can go do things that were previously inconceivable! Last night "I" "made" 3D boids swarm with directional color and perlin noise turbulence. "I" "did" this without knowing how to do the math for any of those things. (My total involvement at the source level was…
Yes but did you learn anything?
Shell scripting was something that I failed to get any real traction with for decades, and since letting AI help me write dozens of shell scripts, I find that I have gained a basic level of proficiency. (i.e. I found that I had become relatively fluent in writing them even without assistance, which surprised me!)
It ties in with the Input Hypothesis of language acquisition. More volume in = more opportunities for brain to find the patterns, and learn them naturally.
That doesn't work for the approach where you don't look at the code at all, though. Which seems to depend on your goals for the project.
For the boids thing, the math isn't something I enjoy doing manually anyway (I've done that for the last 15 years and it always felt like pulling teeth), so the main learning I'd get there would be at the applied level... How to tweak the Perlin noise to get the result I want, rather than how or why it works in the first place.
Earlier quoted context omitted.
In some ways, I'd say we're in a software dark age. In 40 years, we'll still have C, bash, grep, and Mario ROMs, but practically none of the software written today will still be around. That's by design. SaaS is a rent seeking business model. But I think it also applies to most code written in JS, Python, C#, Go, Rust, etc. There are too many dependencies. There's no way you'll be able to take a repo from 2026 and sp…
> That's by design. SaaS is a rent seeking business model. Not all software now is SaaS, but unfortunately it is too common now. > But I think it also applies to most code written in JS, Python, C#, Go, Rust, etc. There are too many dependencies. Some people (including myself) prefer to write programs without too many dependencies, in order to avoid that problem. Other things also help, including some people write pr…
I dont get the hype.. And I dont think we will reach peak AI coding performance any time soon. Yes, watching an LLM spit out lots of code is for sure mesmerizing. Small tasks usually work ok, code kinda compiles, so for some scenarios it can work out.. BUT anyone serious about software development can see how piece of CRAP the code is. LLMs are great tools overall, great to bounce ideas, great to get shit done. If yo…
The hard part is always the last 20%.
