Using coding assistance tools to revive projects you never were going to finish
blog.matthewbrunelle.com242 points by speckx 13 hours ago
242 points by speckx 13 hours ago
I have revamped my home networking setup, installed raspberry pi, setup adguard on it for the home network, migrated my jellyfin set-up to it, integrated all these devices on tailscale, dealt with physical LAN point limitations by setting up a switch, repurposed old router to get around ISP imposed limitations, setup a three tier backup solution and so on. In themselves they are not particularly challenging but taken together, these personal projects had been pending for years.
Not any more. Few weekends and everything has been implemented and I have learned a ton in the process. It has been great fun doing this turbo charged tinkering. I think personal projects are where LLMs shine the brightest.
It’s great. I have a stupendous amount of personal software now. Yesterday was a native text editor that was fully integrated into my mediawiki install and would autocomplete links and make syntax easier to use.
No one could have built this software but me because it’s worth nothing to others. And I couldn’t build it because it takes too long. But when I’m using an agent to code the limited resource is my attention which actually does fine so long as every free brain cycle is on a task. So these personal things are great to throw into my tab loop to occupy a free slot.
These have been wonderful times.
I finished a mod for Quake 2 I started in 1998 finally a few weeks ago. AI is really helping me get past the COVID burnout I was running of too many projects I half did. Fixed terminals (an rdp tool) today. Working on OpenRA bugs I opened issues 10 years ago now - engine is 10x faster and pathfinding mostly works properly.
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 or write docs for people who'll never use it. Just solve exactly your problem and move on.
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
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 = not giving up". Its been awesome at game dev, I gave him game design ideas, he comes with working code. I gave him papers about procedural algos, and he comes with the implementation, brainstorm items, create graphic assets (he created a set of procedural 2d generators as external tools), he even helped me build the lore. These have been one of the most fun times using a computer in a long time. Claude Code + Godot = fun. Going back to it.
I think this is the first time I've seen someone refer to an LLM as "he" rather than "it". No judgement, but I definitely found it interesting (and disconcerting).
I've heard it quite a bit before, but mostly from second-language speakers whose first language don't have impersonal third-person pronouns - e.g. French uses "il" or "elle" for all of "he", "she" or "it".
It doesn't help that the marketing leans heavily on anthropomorphizing LLMs either, IMHO.
It's not weird if it comes from ESL. At least in portuguese there's no "it" equivalent for pronouns or any other neutral artifact in the language, in other words, everything has a gender, even an AI model, the same goes for objects e.g.: knife(she), fork(he), spoon(she), plate(he).
People often commit mistakes regarding that, the same way we don't have "they" as pronoun to someone we don't know the gender, so we address to these people as "dele(dela)" (masculine and feminine pronouns).
But if this is coming from someone who has english as a primary language it's definetely weird to treat models as person
Weird. Don’t you have an equivalent to the Spanish “eso, esa”? Gendered object.
Portuguese is the same as Spanish here. In both cases you would avoid using a pronoun.
Like how in English you’d say “it helps me …” but in Spanish just “me ayuda …”
It’s funny with someone coming from Mandarin. There’s no separate he/she/it in spoken Mandarin, so they tend to mix up “he” and “she.” It sounds very strange and gives me some idea of what French speakers must go through when they hear me say “le voiture” or whatever.
I took a few semesters of Dutch in college, and it has both gendered and neuter nouns for non-human objects. Interestingly though, the professor told us that in the northern parts of the Netherlands people don't really bother using the feminine ones ever and refer to every non-human gendered noun as masculine, which apparently also includes animals, meaning that a sizable portion of Dutch speakers will refer to cows using masculine language.
Because the article for masculine and feminine are the same (“de”) so absolutely nobody knows the gender of anything.
Source: am Dutch. Can’t wait for us to just ditch gendered nouns.
Dutch is one of the few languages where it's actually pretty plausible for something like this to happen! It blew my mind that sometimes you'll all (or I guess more specifically your government) will make changes to the language to clean up issues, but I guess that's one of the benefits to having a language that's mostly based in one country (and some seemingly political baggage for the few others with any significant number of speakers; my professor said that Flemish is basically also Dutch, but my naive impression is that the half of Belgium who speak it might not be happy with that description).
I believe this is common to all the Romance languages.
In the Canadian French dialect all the swear words are incredibly versatile and church-related such as "osti" which I believe refers to the Eucharist.
It just so happens that for nouns beginning with a bowel, you drop the e or the a from le/la, and use an apostrophe.
So if you don't know if it's "le porte" or "la porte" you can use my favorite trick which is to shove osti in there and say "l'osti de porte" which roughly translates to "the goddamn door". You can do this for any noun in French, and Canadian French speakers will get it, though people from France will make fun of you.
As a native German speaker, I have also referred to a chatbot in English as "he", and similar to you, a native English speaker, felt jarred by it. It was definitely not out of any personification or humanization though. In German, I would say it is "der Chatbot" (from "der Roboter"), which in German is a male noun so I would refer to it as "er" (the male pronoun) - which in my head I autotranslated to "he". Most of the time, though, I think of it (and refer to it) as an LLM, which is "das Sprachmodell" (neutrum), so I automatically translate it to "it".
So that's another, maybe more harmless reason for it.
I mean, both in English and in german, that's how you would talk to a dog. "Er hat in die Ecke gepinkelt"/"He peed in the corner" (or "she", if it's a female dog).
I don't know what is jarring talking about the chatbot like that.
It may be creepier if you said "she wrote that program for me" as you now assign a specific gender to the chatbot.
I recognise I am revealing a different type of ambient misogyny in my thinking, but choosing to gender an LLM as feminine gives me “I played tomb raider because I enjoy looking at women” vibes. Like somehow “she” is more of a conscious choice than “he” and comes with all the baggage of all cultural differences between genders, when neither choice should do that.
Curiously though I don’t get the same sensation when technologies are gendered by other people. I honestly don’t recall thinking about it when Apple released Siri. (Now I’m second-guessing myself and wondering if I should’ve reacted negatively towards feminine being the default for someone in a personal assistant role.)
I wouldn't read too much into it, it's natural for non native speakers. In Spanish for example, objects have grammatical gender as well, so it's easy to slip.
Reminds me of the main character of the show Mrs Davis. She insists on calling the ai it through the entire show.
It is common amongst French, Dutch etc speakers where saying "it said x" sounds unnatural.
Russian too. There is a subset of words which are referred to as "it", but for most words "he" or "she" are used regardless of whether these are living things or not. With loanwords we just decide by similarity to other words. Claude is definitely a "he" as the word is the same as a common male name.
This trips me up occasionally when I'm translating things into English. Once, when I referred to an indefinite gender player character in a gacha game as a "he" (because the word "player" is a "he"), quite a few people got mad! Even though in my head I was never trying to imply one way or the other.
For future reference, in this case you could use the singular "they" to refer to an ambiguously-gendered person or character. "<MC> drew their sword, for they would not tolerate such vile deeds."
There's an analyst at my job who calls it "he", who is a native English speaker himself, which I guess is because it's "Claude" (as in Claude Shannon) Code.
I mean we have all met that one cretin who will discuss over chat by pasting bulletpoints from an LLM. No wonder some of them think it is a living person!
> No judgment
Yes judgment. Loads of it. Judge away.
This is just bizarre. Do not refer to this product of marketing-technology as you refer to a person. EVER.
The article itself is also probably an attempt at marketing the LLMs too. They are now quite desperate. Expect to see a flood of such "independent" articles over the next 12 mo ths.
What’s fun for me these days is picking up a project I started with an LLM doing agent driven development a few months ago or even a year ago and hit a wall and stopped being able to be picked up by the latest version of Claude and/or codex and bringing it further. Some can now launch some still are too complex for the agent to build. But, it’s getting easier and easier to build personal apps. We are not far off from being able to say “Alexa, build me an app on my iPhone that lets me take pictures of the food in my fridge to compile the nutritional benefits and sync it with my workout app then compare it to the ideal ingredients I should eat based on my fitness goals in my health app and have it set to send me emails where it can find me better ingredients to buy that are cost effective, local, and meet my diet restrictions” and in 15 minutes that app suddenly exists.
Same I purposefully have a number of over ambitious project out of distribution entirely to test so failure mode, mostly games, when one works, well I gained a new game. Can't wait for my 10 player battleship game on a 100x100 grid to be functional.
I’d love to see your attempts at this. I think we’re close to something vaguely resembling this at a first glance but nothing that actually works.
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.
I had very few issues, sometimes I had to direct CC to the godot docs and we could keep moving. Specifically the tile configuration was a "read the docs" moment. All the functionality is available through code, so nothing CC can't reach afaik. Is there any LLM oriented game engine?
I have taken many stabs at it and Claude will produce stuff but the output is very far away from useful. E.g. "I've created a road and beautiful trees" and what I see is a mess of colors and shapes.
I concur it's bad at directly visual concepts, your prompt is akin to the svg pelican. What I do is asking him for procedural algos, automatas, quadtrees, layered noises, and rig those into the game. Yes, it can't "make the next gta", but with a reasonable scope and knowing what it does best, it has been very easy for me to produce satisfying results.
My problem is I don't really have video game engineering experience. I was going off a concept that a different AI nailed with video creation and was trying to replicate it in the game engine.
Would you care to show a few pictures?
Sure! Two are gameplay pics. An enemy sprite sheet generation, and the results of the map generators. Of course these are basic placeholders for a few hours of work, but I will definitely go heavy on this route with more layering and details.
https://drive.google.com/file/d/1A7kfcjHjSmCNidqc9t731uoglzL... https://drive.google.com/file/d/1Bl_n0ECqc78LGGf7SsOx38mRUOP... https://drive.google.com/file/d/1JMcgzqcnZ2ncboeyAXvscRWagqR... https://drive.google.com/file/d/1-luJ6y7YslNfwmFnCdIDbJ871i0... https://drive.google.com/file/d/14n4TLAVywk_1GMhLLGOuukQwUmb...
Are any LLMs suited at directly modifying game scene/asset/prefabs for any engine?
Bevy is a great engine for LLM-based games because it's 100% code. I'm toying with a few things in it, one of them is an entire-planet economic simulation, and it scales well up to a million dead tiles and 10k-50k live tiles on Apple Silicon, pretty impressive.
On the topic of procedural, one thing I experiment with is having the llm part of the procedural loop.
Sort of writing a narrative on top live.
Unfortunately, local models are still a bit slow and weak but was interesting to see what it came up with nonetheless.
> he explicitly pushed into "lets have V0 game play loop finished,
> he even helped me build the lore. These have been one of the most fun times using a computer in a long time.
Such a warm, touching story about a friendship between a grown up man and his neural network. But at least I had a good, roaring laugh reading this nonsense, thank you for that!
How snarky. You are conflating friendship with admiration for the effectiveness of newfound tool. If it's the "he" that triggers you, feel free to replace with "it". It's just a second-language artifact.
I dunno man. He sounded like he found a new friend in 'him' to me. And it was genuinely hilarious. It took me a while to stop laughing.
> 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 functionality?
None of these are insurmountable, but they require some careful setup.
Posts like this dont make me laugh; they just make me roll my eyes.
Either the OP has not done what they claim.
Or they have spent a lot more time and effort on it than they claim.
> I gave him game design ideas, he comes with working code. I gave him papers about procedural algos, and he comes with the implementation, brainstorm items, create graphic assets (he created a set of procedural 2d generators as external tools), he even helped me build the lore.
Such a sweet story about a boy and his AI.
Unfortunately, I also dont believe in fairytales.
Instead of waving your hands wildly about AI, post some videos and code of the results.
This is hackernews, not hypenews.
OP never said Claude made a whole game from scratch though, nor are they saying Claude is doing everything without any human contributing to the project, nor are they saying they haven't spent a lot of time and effort on it. Just that it's made it fun and more accessible and it's gotten them excited about something they abandoned.
Here's a bullet point list of the things Claude's done according to OP:
* it picked up the general path immediately
* he explicitly pushed into "lets have V0 game play loop finished, then we can compound and have fun = not giving up".
* [I gave him game design ideas,] he comes with working code.
* [I gave him papers about procedural algos,] and he comes with the implementation
* brainstorm[ed] items
* create[d] graphic assets
* he created a set of procedural 2d generators as external tools
* he even helped me build the lore.
Every one of these are plausible in isolation.
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 tests and check for debugger warnings. For anything more complex it can wire debug info anywhere. Godot is fully code based so you can make the analogy with any other framework you used AI assistants with.
No sure about what you can't believe about my statements. CC implementing algo from a paper? That it can brainstorm item or lore ideas? I don't seem to be claiming anything out of the common usage of LLMs
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. I threw it a Claude Code, told it what I wanted the graphical interface to look like, and let it run.
It got an app exactly what I wanted, and even found a bug in the date parser that I hadn't noticed. I now have it running in the corner of my screen at all times.
The next app I'm going to build is an iPhone app that turns off all my morning alarms when the kids' don't have school. Something I've wanted forever, but never could build because I know nothing about making iPhone apps and don't have time to learn (because of the aforementioned children).
Claude Code is brilliant for personal apps. The code quality doesn't really matter, so you can just take what it gives you and use it.
> 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 now living in the menu bar of my Mac, doing everything I wanted and more.
Particularly enlightening to me was the result of my asking CC for suggestions for additional features. It gave me a long list of ideas I hadn’t considered, I chose the ones I wanted, and it implemented them.
Two days ago, I decided I wanted a dedicated markdown editor for my own use—something like the new markdown editing component in LibreOffice [2] but smaller and lighter. I asked the new GPT 5.5 to prepare an outline of such a program, and I had CC implement it. After two vibe coding sessions, I now have a lightweight native Mac app that does nearly everything I want: open and create markdown files, edit them in a word-processing-like environment, and save them with canonical markdown formatting. It doesn’t handle markdown tables yet; I’ll try to get CC to implement that feature later today.
[1] https://simonwillison.net/2026/Mar/27/vibe-coding-swiftui/
Absolutely. I love building things, but sometimes I want something built. LLM assistance is great for when I want a personal tool, code quality be damned, for a specific purpose, without it taking over a weekend.
You don’t need to build an app. You can use the built in Shortcuts app.
create a shortcut that turns off all alarms. Can have it read your calendar or whatever as signal to determine if alarms should be on/off for a certain day/time and have it run at a regular schedule.
I could, but what's the fun in that!?
(But in seriousness, I hadn't considered using shortcuts. It's not clear it's extensible enough to do exactly what I want, but I'll look into it)
It’s tedious but likely possible.
If you really want to engage an LLM to help point it towards Cherri (https://github.com/electrikmilk/cherri) to help with implementation
Where's the fun in purchasing an app from Anthropic?
Co-working with AI is an important skill to learn these days. Similar to paying a bit for AWS for your personal projects as a good way to learn all the AWS tools for your career.
What is the skill that needs to be learned? I've been forced to vibe code everything at work, there's no skill required to ask Claude code to do something.
Meh. That's fine if you really don't want to build things, and are mainly concerned about increasing your market value.
If you like creating, buying software from Anthropic is boring as hell.
Three notetaking app attempts sitting in my private repos, all stalled at the gap between idea and free time. With Claude Code I finally got the one I really wanted out in two months. Building it has been the best hobby I've found. Beats games or scrolling. When you've been carrying an idea for years, the app that finally ships has more of you in it, and I'd bet we'll see a lot more of these from solo builders.
But who will buy it? No knocks against building old projects, but the market will be flooded with extremely speciality projects. I miss when every app had a spec on the box. I think we need something like that for usage. A new modeling language or something.
>the market will be flooded with extremely speciality projects
All the personal tools described in this thread are duct tape and bubblegum under the hood and nowhere near productionizable. That's what Claude Code makes for you.
The whole point is that for personal tools, code quality never really mattered since it's never going to be exposed to the public or be iterated upon by a revolving door team of devs like real software products. These are all highly overfitted tools that shave off like 15 seconds of time in the day for some particular person.
It's almost exactly like having a 3D printer for software, with exactly the kind of quality that a present-day 3D printer gives you.
Who cares? Nothing wrong with trying to make a product to sell, but projects dont have to be to sell. I've been having a blast lately working on an old game engine I started during covid and getting sidetracked into some new projects. None of them will ever make me a dime but I'm learning a ton and having fun.
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 like to leave side projects for the good of the spirit. An exception could be results for a greater good that one really believes in. This can give purpose and enrich the process and experience of doing.
I have a lot of hobbies. Programming is one of them, but not the only one. There are times that some piece of software would help me with one of my hobbies, but I don't want to steal time from hobby X to build the software. And often these don't involve the kind of coding that I want to be doing for fun. This has been a sweet spot for LLM-aided coding for me. I've built several hobby helper apps where the goal was making one of my other hobbies more fun rather than programming. It's still hobby time, not work, but the hobby is not coding.
If you're coding for the sake of coding, maybe. If you have itches to scratch and ambitions, but can't summon the motivation or the time, then how is that "working in your free time"? A project that used to take up my entire weekend or vacation can now be knocked up in 15 minutes. That's the exact opposite of working.
What is coding for the sake of coding? I don't think anyone does that. Its about solving puzzles, using your brain, learning by doing, creating things- none of that happens when you use llm coding tools. Instead all you're doing is creating more cheap mediocre throwaway crap just because you can.
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 open source. I got HUNDREDS of comments from "LinkedIn-type people" all big name engineers that wouldn't HIRE me for anything but either made comments like "looking forward to integrating this into our workflows" or "not the first time someone tried to do this..."
Either way, instead of feeling motivated, I got the worst feeling that I'm doing all this work and people are either going to just take advantage of it and get the credit for "finding" it, or criticize it simply because it's not for them.
It bummed me out so bad that I stopped work on it entirely for like a month.
Anyway I finally came to look at it the way you mentioned. What I LIKED was the process of learning Qt and seeing my old programs come alive.
So instead, it's my "project car" now. I build it up and tear it down all the time. Totally redesign the data models just to see what advantages different designs can give me. Try make my own graphical views. Try implementing language translations.
It's been "finished" for a while now but I probably have five completely different-under-the-hood versions of it and THAT is what has been fun.
I use it constantly all day at work and I never mentioned it on LinkedIn again lol
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.
In the time I’ve had agents I’ve never abandoned more projects. Vibe coding especially just leads me to feel no attachment. I don’t feel proud to put my name on it.
Despite coding from a young age I always thought that I cared more about the outcome than the code. Turns out that’s not entirely the case.
I’ve had a similar experience.
Having better tools really makes a difference when revisiting old or half-finished projects.
I once had a project for novice freelancers. The idea was to take your abandoned fumble and put multiple people on it at 3rd world rates. There are lots of people in cheap coutries who can somewhat code. You can aford hiring someone for [say] 3 euro per day. If they describe where they got stuck in the daily progres report you can look at it and help a bit or not and Just let them figure it out.
You can pay more of course, buy them a computer, an internet connecties, books, courses, even an office but it isnt required.
Just pay 60 per project every 4 weeks and ignore it. If interesting progress happens its fun to look at.
> In my mind there are different buckets for personal projects. One is things I do to learn and grow and the other is things I really wish existed.
Pretty much 100% of projects I've done with vibe coding/engineering is in the second category. Stuff I need that either doesn't exist or exists, but is either horribly complex to configure or is a mess of 420 features even though I just need one of them.
It's a lot easier for me to implement that one specific feature just for myself than keep vigilant on an existing app's eventual scope creep as it progresses to the eventual ability to read email[0] =).
With AI coding I was able to build three applications I always wanted but never had time to code them.
Now it is different in a way — I don’t have time to use them.
it's a top affordance of AI because pause development usually over complexity I can't manage or knowledge gap that I can't close in time to sustain momentum. Not only are those roadblocks a non-issue, my perspective shifts from in-the-weeds hacking to a perch with meta view to take the project to completion or maybe beyond previous goals. win-win to the power of win
The tooling landscape has changed so much in the last two years that I find myself re-evaluating automation setups that were solid 18 months ago. The time investment to rebuild is real but the efficiency gains on the other side are worth it for anything you're doing more than a few times a week.
Every time I see a story like this I like to play the game "does this person just happen to work for a company that sells AI solutions?". And yes, yes they do. Almost never will see you a story promoting AI solutions from someone that isn't directly involved in selling AI solutions.
+1 and - The title has that weird corpo media "here is why you should not quiet quit" vibe to it, doesn'it?
In 2020 I was in the Codemirror forums trying to get help with a project that replaces React in GraphiQL for Svelte. It was too difficult for me to figure out so I shelved it. Yesterday I asked Claude to make this happen and it referenced that very thread I made.
Anyhoo, I'm working on making it pretty (it works!!) before integrating it into my opinionated GraphQL server[1].
There really is no excuse for NOT being the change you wish to see in the world anymore.
---
We have closed-source and open-source software, I think the next phase is going to be self-source or llm-source software (not sure what the term will ultimately end up being), but basically if you have a need for something that is not filled exactly by any app, you will just give the spec to an LLM and in X amount of minutes/hours you will have bespoke software built just for you to use personally, fully tested and to spec. For example, I still haven't found a workout/weight lifting tracking app that does 100% of what I want and at this point I may just build it myself because I could probably do it in half a day with claude and won't have to pay any annoying subscription fees. Maybe it'll still be called AI slop but if it works it works.
This hits home. I have ~10 abandoned side projects.
I just shipped one this week (ToolRelay - toolrelay.online) by forcing myself to focus on a single vertical slice end-to-end and stop opening new repos.
The pattern that broke for me: stop building, start distributing. The build phase gives a dopamine hit; distribution feels painful, so we keep building instead.
Curious — was the AI assistance helping you build new features, or helping you re-understand your own old code months later?
I checked your link and fail to see how that is a pre AI project that you are only completing now, it is obviously a recent concept. Also your username matches the project, so this seems mostly like a lame attempt to shill your product by “joining the conversation”
There certainly is some relaxing value in working on projects to vibe code them; but not enough to pay some random corporation. Get yourself a Mac Studio or AMD395+ and pi or opencode, and a few plugins and they're pretty capable. Since they're not speed demons but reliable compaions who are always there, you don't ever feel compelled to constantly attend to whatever they're doing.
And when you inevitably get bored with it, well, you've not done much anyway. You can always get back up to speed in a month and have the LLM remind you of what it was doing.
> And when you inevitably get bored with it, well, you've not done much anyway.
I'm very interested in Local LLMs but the cheapest Mac Studio right now is more expensive than 8 years of a Claude Code Pro subscription, and incomparably slower/less capable. If I get bored with it, I will have a piece of unused hardware and a couple grand less in my bank account.
I have opencode with qwen 3.6 on my local machine. Just get the setup right and it's surprisingly fun to work with.
I had a ton of fun setting up and trying it out locally (also opencode and one of the qwens.) I still don't have hardware powerful enough to feel like it's meaningfully productive, but all the learning I had to do (and all the bonus things I got curious about as the curtain peeled back) got my nerd brain all worked up, and finally seeing it work was exciting in that cool-new-experience way you don't often get to enjoy :)
Yeah this is exactly how I felt! Never really felt excited about llms or agentic workflows before. Getting everything setup 100% local and tweaking it to exactly what I want and having it actually working quite well has been a really cool experience.
If you already have a gaming pc, then it's worth exploring as the cost of boredom is negligible.
I did tinker a lil with mine! RTX3080 with 10GB VRAM, 5600x with 64GB DDR4 - not very good but it was very fun and exciting to tinker with :)
My partner on the otherhand has an M3 Max 64GB which I've had way more success with. Setting up opencode and doing a tiny spec-driven Rust project and watching it kiiinda work was extraordinarily exciting!
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.
I find $200/month for the pro/max subscriptions cost prohibivitve, but as a software enginere $20/month is just lunch.
And with a Claude or GPT $20 Subscription, i can do other fun things too like using it for real things (emails) or image generation.
A Mac Studio or AMD395 is neither of it. And its not just a basic setup either. I need to buy it, configure it, put it somewhere. That alone is a grand and more + a whole weekend.
You need to factor in the constant value proposition that cloud providers will absolutely drive you to in the next 2 years; even if you're not an AI hater, you should listen to ed zitron's description of the value props these clouds require to make a profit for their VC backers.
This means oyu may be opinionated today on something you will not have tomorrow, 6 months, a year. All that work flow you salivate over can be ripped away.
If you're fine with that, and you've "escaped the permanent underclass" congrats, this opinion is not for you.
Buying hardware is paying a "random corporation". Make the massive hardware purchase after finding out if you have enough demand to buy rather than rent,
Yeah. I setup opencode + qwen 3.6 last weekend.
It's actually really cool to have it work on some internal tooling and stuff while I work on my primary projects.
I'm surprised how easy it is to setup and that it can handle modestly complex planning and development flows.
Sounds a lot like that disgusti g corporate press propaganda tbh, of the "eat less avocado toast if you cant afford rent" variant. Is the AI mainstream that desperate in their relentlesss push for adoption of their bullshit text generators?
But why give Anthropic/openai our money? Nonsense. Use open models
Quality, simplicity, speed.
I have a ML Setup with 2 4090 and 128gb of ram, its warm when i use them for finetuning or batch processes.
I do not run them for coding. Its a lot easier and nicer to play around with better models for just 20 $.
The author got $50 free credits.
Also Anthropic is by far the best, open (local) models are glorified autocomplete at best unless you casually have 20k€ worth of hardware at home.
Disagree. Qwen 3.6 and opencode have built and helped plan entire feature sets such as vectorizing and searching, setting up UI to manage categorized search data. Some test systems around this, etc.
Very usable locally assuming you setup your local tooling correctly and you are an actual programmer who can generally help drive this stuff correctly and not just a vibe coder.
How big of a Qwen model are you running that can plan and implement entire feature sets?
I’ve tried multiple that I can run locally and they’re all very much just glorified autocomplete, but slower - on a M4 Max MacBook
Why assume local when you can easily use any of the open models via openrouter or any number of similar services.
The OP said “ But why give Anthropic/openai our money? Nonsense. Use open models”
Then I’d be giving money to openrouter and a Chinese model provider, is that better?
Yes, it is better. They are releasing open models, unlike Anthropic. Additionally other (non-chinese) companies run the open models, so if that is the issue you have options.
Yes, you can revive it into worthless slop. Learning next to nothing for yourself and achieving a hollow sense of satisfaction at best.
Maybe even shamelessly post it as a Show HN along with the other 99% of worthless slop submissions there.
I want app X. I know how to code it but it'll take a whole weekend/vacation days. I would learn nothing. Now I can use AI to make it. What exactly am I losing here?
Your dignity.
As you perch comfortably in your Throne of Purity, it's worth remembering that the average software developer sits on top of 10+ layers of abstraction (not counting hardware).
projects you were never going to finish should stay projects that are never finished :)
effort needed used to be a gatekeeper for bad ideas
now Claude will gas you up and tell you your bad ideas are actually the most amazing thing it’s ever heard
[dead]
[dead]
[dead]
[dead]
[dead]
[stub for offtopicness]
[we've hopefully deprovokified the title now]
To use agentic what? Off topic as heck but I really dislike this trend of coercing adjectives into true nominals - we're using programmatic! - like some sort of even-more-obnoxious variant on the verb to noun ('the ask') process.
Why does it bother me so? I have no idea.
blame the hn title rules (although i would just have substituted "AI")
i doubt anyone is nouning "agentic" of their own accord (yet)
It’s ok to use coding assistance tools for anything you’d like! Not that you needed the permission of some random on the internet.
[dead]
What is the point of using AI for a side project? Isn’t the point of a side project to A) have fun writing code or B) challenge yourself or C) learn something new, and usually all 3? Slopping out random stuff you have no attachment to, taught you nothing, and that feels bad to pass off as your own work accomplishes nothing.
> What is the point of using AI for a side project
Why is this so hard for you to understand?
> Slopping out random stuff you have no attachment to, taught you nothing, and that feels bad to pass off as your own work accomplishes nothing.
You seem frustrated that people have different motivations than you. Have you looked into getting an AI girlfriend?
D) to solve a problem in your personal life? To make an app that you wish existed but didn't?
[flagged]