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

Using coding assistance tools to revive projects you never were going to finish

blog.matthewbrunelle.com

Post reply on HN
Print view View original

191–200 of 263 posts

Re: Using coding assistance tools to revive projects you never were going to finish

#191

Post by tasuki »

ogig wrote: post #7

My most abandoned type of projects are video games. I have a folder with tens of abandoned projects, I re-frame them as experiments at that point. This last week I decided to give Claude a go at one of these, and it's been a blast, it picked up the general path immediately. Since I said to CC they were abandon projects, he explicitly pushed into "lets have V0 game play loop finished, then we can compound and have fun…

> I have a folder with tens of abandoned projects, I re-frame them as experiments at that point.

Interesting, I have just the opposite situation: I have a folder with tens of experiments, many of which have become actual projects at this point.

Re: Using coding assistance tools to revive projects you never were going to finish

#192

Post by samiv »

kowbell wrote: post #36
arcatek wrote: post #17

Earlier quoted context omitted.

Isn't Godot a little ill-designed to work well with LLMs? for example I ended up a couple of times with incorrect tres files, and letting the llm generate IDs feel a little fragile.

Are any LLMs suited at directly modifying game scene/asset/prefabs for any engine?

I have a simple script system in my editor that is designed to let the chatbot (Claude) to work on the content. The script interface lets it to import assets into the project, open them for editing, take a screenshot, export content (and few other things). All data is in JSON so it typically figures out the data format quite fast and easily.

Here screenshots of some UI styles that it generated.

https://github.com/ensisoft/detonator/tree/master/uikit

Re: Using coding assistance tools to revive projects you never were going to finish

#193

Post by mbtrilla »

My experience matched this almost too closely. Had a comparison-aggregator side project sitting at maybe 20% done for over a year. I'd open it once a month, scroll through the still-need-to-do list, get tired, close the tab. Pairing with Claude for a couple of weekends got me past the half-built wall. The thing that surprised me wasn't raw speed. It was that I stopped having to spend an hour reloading my own old code into my head before I could do anything. That re-entry tax is what always killed it for me. The hype is annoying but the people dunking on these tools mostly aren't using them for the boring stuff they're actually decent at.

Re: Using coding assistance tools to revive projects you never were going to finish

#194

Post by cxr »

AnotherGoodName wrote: post #137
saadn92 wrote: post #130

Earlier quoted context omitted.

It's crazy. I have something like 120 personal tools at this point and the pattern you describe is exactly right. The bottleneck moved from implementation to context switching. I started keeping a markdown file at the root of every project that captures state and next steps whenever I stop working on it, purely so I can resume without the 20-minute "wait where was I" tax. There's just no pressure to handle edge cases…

I’ve been asking it to make some of my game tools into static websites where possible. I did pay the $10 for the following domains but i’m ok with that so i can share some of the fun things that come out of the agent. grandcheaten.com - a save game editor and guide for jagged alliance 3 thedailycheat.com - a save game editor for newstower

Itch.io allows for browser-based app distribution and is probably a better path to a large audience—especially those interested in the two examples you listed—than a custom domain is.

It's not well-known, but Itch's offline Steam equivalent (https://itch.io/app>) is also open source.

Re: Using coding assistance tools to revive projects you never were going to finish

#195

Post by cyanydeez »

kowbell wrote: post #132
cyanydeez wrote: post #71

Earlier quoted context omitted.

AMD 395+ w/128gb is all you need. the idea that mac studio is the default is a nerdfest.

I admittedly haven't done a ton of research lately on AI capable PC hardware because of how nuts prices are right now, so I might be missing something... ...but all the AMD 395+ machines I can find are even more expensive than the aforementioned cheapest Mac Studio. Mac Studio starts at $2,000 (only 32GB), AMD 395+ 128GB machines seem to start at $3,000 from what I can see.

the QWEN-3.5-CODER-NEXT fits in half the 128GB and the rest for context. with the right plugins, particularly context pruning, ive got it running over night by writing plans then implementing.

i do not know if theres a smaller model with same capability, but model size and context window at 128 seems like a sweet spot.

token speed really isnt a bother because im either just multitasking or working on the filling in the missing details.

regardless, i think comparing first VRAM sizes w/target model then speed for your cost efficiency. plus, a healthy skepticism of mac hardware costs.

Re: Using coding assistance tools to revive projects you never were going to finish

#196

Post by ZihangZ »

ogig wrote: post #115
noodletheworld wrote: post #103

Earlier quoted context omitted.

> the effectiveness of newfound tool …and yet, most people continue to say that non standard tooling ecosystems, where the agent cannot run and validate the code it writes, remain difficult and unproductive. “I just pointed CC at godot and it made a game! This is sooo good” …is a fairytale. What tooling are you using to make it run and compile the code? How is it iterating on the project without breaking existing fun…

But I had already answered, before your comment, with screenshots broadly showing the current state and the result of the generators. You imply I'm merely "pointing CC at godot and it made a game"; I never said it was simple, required no previous knowledge, that it was instant or that the game was done. I do have a careful setup involving CI and isolation. Godot provides a headless mode. CC runs python scripts to run…

+1 to the CI/isolation point. That is the part that makes these setups work for me too: make the failure cheap to reproduce, make stderr visible, make the agent rerun the same command after the patch. A lot of bad agent behavior is really just "it never got a clean signal".

The part that still bites me is across sessions. A tight loop fixes this run, but next week the agent can walk into the same rake again: same wrong import path, same misuse of an internal API, same CI-only dependency issue. After patching the same class of failure a few times, I started writing those down outside the chat context so the next run sees the failure pattern before it guesses.

Re: Using coding assistance tools to revive projects you never were going to finish

#197

Post by nickthegreek »

rhubarbtree wrote: post #185
potomak wrote: post #135

I prompted Claude code from my phone to revive Draw!, a pixel art editor I first published 15 years ago as an exploration using Redis as a DB. The new version is live at http://pixel.drawbang.com after 1 week of prompting Opus 4.6 with a max subscription.

Could you try to revive it by hand? I’m curious as to how long it would have taken.

Absolutely insane request.

Re: Using coding assistance tools to revive projects you never were going to finish

#198

Post by bbkane »

tkgally wrote: post #104
jedberg wrote: post #53

12 years ago I tried to make a simple app for myself. It would display bars that got smaller as the day/week/month got shorter, and would show the weather as a set of bars between max temp and min, cloud cover, etc. I got it working well enough to display what I wanted in text and ascii, but I could never get the interface good enough to want to use it daily, and certainly couldn't get the graphical interface working…

> Claude Code is brilliant for personal apps. Agreed. The clipboard manager I had been using on my Macs for many years started flaking out after an OS update. The similar apps in the App Store didn’t seem to have the functionality I was looking for. So inspired by a Simon Willison blog post [1] about vibe coding SwiftUI apps, I had Claude Code create one for me. It took a few iterations to get it working, but it is n…

Could you share the source to your Markdown editor? I'm always looking for new ones

Re: Using coding assistance tools to revive projects you never were going to finish

#199

Post by bbkane »

w33n1s wrote: post #63
codybloem wrote: post #56

When it comes to side projects, most of the time, if the spirit isn't willing I find it not worth doing. Process/experience over results, I call leisure. Results over process, I call work. If you have many side projects done mainly for the results, than you are working in your free time, and looking at it like that: is it really free? The modern age already requires of us more results than the spirit is good for. I l…

I share this view, I think it's very healthy. I've been programming for 30+ years now, but I've always been fine with command line applications. Only recently I started getting into Qt to add a UI and turn my stuff into a real desktop application. It's been a real steep learning curve but I'm finally over it more or less. Anyway I posted a screenshot of my application on LinkedIn, and mentioned it would be free and o…

I've been doing the same thing with my CLI framework. Rethinking and rebuilding with no pressure to finish is a lot of fun.

I've been using the CHANGELOG [0] as a "blog" explaining WHY I made the changes and that's really been fun to look back and read too

0: https://github.com/bbkane/warg/blob/master/CHANGELOG.md

Post reply on HN