Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Building a Personal AI Factory

john-rush.com

Post reply on HN
Print view View original

111–120 of 167 posts

Re: Building a Personal AI Factory

#111

Post by sroussey »

1dom wrote: post #100
simonw wrote: post #53

Earlier quoted context omitted.

I think the hardest problem in computer science right now may be coming up with an LLM demo that doesn't get called "pretty trivial".

I'm very pro LLM and AI. But I completely agree with the comment about how many pieces praising LLMs are doing so with trivial examples. Trivial might not be the right word, but I can't think of a better one that doesn't have a negative connotation, but this shouldn't be negative. Your examples are good and useful, and capture a bunch of tasks a software engineer would do. I'd say your mandelbrot debug and the LLVM p…

LLMs are best demonstrated with greenfield examples.

Re: Building a Personal AI Factory

#112

Post by addandsubtract »

sussmannbaka wrote: post #98
gerdesj wrote: post #34

Earlier quoted context omitted.

Crack on - this is YC! Why are you not already a unicorn?

As it turns out, the VC potential of Mandelbrot and HelloWorld.py are quite limited :o)

Bakeries have been in business for thousands of years. Should be pretty easy to sell Mandelbrot everywhere around the world.

Re: Building a Personal AI Factory

#113

Post by petesergeant »

stavros wrote: post #97
petesergeant wrote: post #45

Earlier quoted context omitted.

> ppl are getting slowly disillusioned with vibe coding. This is the absolute polar opposite from my experience. I'm in a large non-tech community with a coders channel, and every day we get a few more Claude Code converts. I would say that vibe-coding is moving into the main-stream with experienced, professional developers who were deeply skeptical a few months ago. It's no longer fancy auto-complete: I have myself…

I don't doubt that LLMs are extremely useful for making simple things quickly. I haven't been able to get them to write hard code on their own, though. I was trying to make a sound card with a Pi Pico the other day, and had crackling and popping in the audio. I kept telling Opus to fix that, it kept being absolutely convinced it knows what the problem is every time, and went through multiple iterations of being absol…

> I haven't been able to get them to write hard code on their own, though

For sure, and me neither, for what it's worth. But most of the code I write isn't "hard" code; the hard code is also the stuff I enjoy writing the most. I will note that a few months ago I found them helpful for small things inside the GPT window, and then tried agentic mode (specifically Roo, then Claude Code), and have seen a huge speedup in my ability to get stuff done.

Re: Building a Personal AI Factory

#114

Post by qiine »

webprofusion wrote: post #55

The basic idea is that you can continuously document what your system should do (high level and detailed features), how it should prove it has done that, optionally how you want it to do it (architecture and code style etc). The multi-model AI part is just the (current) tool to help avoid bias and make fine tuned selections for certain parts of the task. Eventually large complex systems will be built and re-built fro…

sorry but again...

https://i.pinimg.com/736x/03/af/06/03af0602a8caa51507717edd6...

Re: Building a Personal AI Factory

#115

Post by CjHuber »

simonw wrote: post #28

My hunch is that this article is going to be almost completely impenetrable to people who haven't yet had the "aha" moment with Claude Code. That's the moment when you let "claude --dangerously-skip-permissions" go to work on a difficult problem and watch it crunch away by itself for a couple of minutes running a bewildering array of tools until the problem is fixed. I had it compile, run and debug a Mandelbrot fract…

Is it that much better than Codex?

Re: Building a Personal AI Factory

#116

Post by j45 »

simonw wrote: post #53
low_common wrote: post #46

Earlier quoted context omitted.

That's a pretty trivial example for one of these IDEs to knock out. Assembly is certainly in their training sets, and obviously docker is too. I've watched cursor absolutely run amok when I let it play around in some of my codebase. I'm bullish it'll get there sooner rather than later, but we're not there yet.

I think the hardest problem in computer science right now may be coming up with an LLM demo that doesn't get called "pretty trivial".

Many big problems are made up of small problems.

Re: Building a Personal AI Factory

#117

Post by j45 »

1dom wrote: post #100
simonw wrote: post #53

Earlier quoted context omitted.

I think the hardest problem in computer science right now may be coming up with an LLM demo that doesn't get called "pretty trivial".

I'm very pro LLM and AI. But I completely agree with the comment about how many pieces praising LLMs are doing so with trivial examples. Trivial might not be the right word, but I can't think of a better one that doesn't have a negative connotation, but this shouldn't be negative. Your examples are good and useful, and capture a bunch of tasks a software engineer would do. I'd say your mandelbrot debug and the LLVM p…

There is a scale somewhere in these types of articles that will emerge.

It might be something being actually new (cutting edge) vs new to someone vs the human mind wanting to have it be novel and different enough as a comparable percentage of the experience of the first time using ChatGPT 4.

There is also the wiring of non-deterministic software frameworks and architectures compared to the deterministic only software development we're used to.

The former is a different thing than the latter.

Re: Building a Personal AI Factory

#118

Post by j45 »

sroussey wrote: post #111
1dom wrote: post #100

Earlier quoted context omitted.

I'm very pro LLM and AI. But I completely agree with the comment about how many pieces praising LLMs are doing so with trivial examples. Trivial might not be the right word, but I can't think of a better one that doesn't have a negative connotation, but this shouldn't be negative. Your examples are good and useful, and capture a bunch of tasks a software engineer would do. I'd say your mandelbrot debug and the LLVM p…

LLMs are best demonstrated with greenfield examples.

Plus, applying non-deterministic algorithms in a deterministic way might not always work the same. The software developers are also changing the frames and terms of reference.

Re: Building a Personal AI Factory

#119

Post by NitpickLawyer »

geekymartian wrote: post #32

ADHD coding, brute forcing product generation until you get it right? Just freaking write the code that you can expand and modify in the future instead of increasing your carbon footprint.

> Just freaking write the code that you can expand and modify in the future instead of

Why is it always this argument? Is it that hard to believe that you can get recent coding assistants to write expandable and maintainable code in 0shot? Have you tried just ... asking for that type of code?

Re: Building a Personal AI Factory

#120

Post by mmarian »

derencius wrote: post #110
mmarian wrote: post #93

And here I am struggling to get Claude to create a nice-looking search bar a la booking.com , with some adjustments for my personal use case; it does ok, but never gets to the end result and once I refreshed my Tailwind knowledge it felt much slower than hand coding. I feel like I'm living in a different world.

I use Claude and Cursor in parallel. cursor is doing great on the ui, I took quick screenshots to instruct the changes I wanted and it got it right.

Cheers! It's hard to keep track of what's good for what.
Post reply on HN