Hacker Newsnew | past | comments | ask | show | jobs | submit | codazoda's commentslogin

I use Sonnit for my personal work and Opus for my professional work.

For my personal stuff, I'm on a small $20 plan, so I need to use tokens conservatively. I was very rarely exceeding limits until I built a Dark Software Factory. It's not as efficient at token use. So, I use Sonnit over Opus here.

At work I have a $100 plan that I rarely exceed so I use Opus. I have access to Fable too, and I did use it a lot while it was new, but I don't find it improves most of my work by too much. I do mostly bug fixing across several hundred repositories with hundreds of thousands of lines of code, mostly written by humans over the past 20-years. These projects interact with each other so I run claude from the root of my sandbox (I was nervous to try this but I'm not looking back now).

I also use Sol as a secondary for my personal work. I pay for it because I like to talk to ChatGPT on the web. Since I already have the subscription, I let Sol write plans for me. It does a better job at certain tasks and it saves me some Claude tokens. Maybe I should consider Terra for the task, but I don't run up against my usage limits for the little bit I use it.

I'm trying to use Gemma 4 12b for some workloads but I haven't mastered the model yet. It's still very experimental for me. I can get work from it but it takes a lot of hand-holding. For local models, however, it's all I have the RAM for.


How is the Dark Software Factory set up? What is it producing?

That is almost to say that the only part of the project that matters is the code. But the code is only a tiny part. I take joy in describing the thing and bringing that vision to life.

You didn't bring anything to life. You just described it.

I mostly agree with this sentiment, and have a hard time describing anything LLM generated as "mine". However, would you say that the designers at Apple, or Steve Jobs for example didn't "bring the Macintosh to life" because they didn't work on any of the engineering or code? It's a hard line to draw.

Leading a collaborative effort can obviously be described as bringing the project to life. People want to feel like they are collaborating with LLMs and are still the visionary in the process. As the performance of these systems improves that becomes less and less the case.

E.g. if Steve Jobs had simply handed a slip of paper to a team that said "make a new kind of computer", then no, he would not have brought the Macintosh to life.


No, its a very easy line to draw. Rallying and bringing together humans is COMPLETELY different than having an LLM do something. They are not comparable.

No you're just drawing a new arbitrary distinction

Completely arbitrary distinction. Effort is not more valuable than the results of the effort. This is a mindset that will keep you trapped.

We’re all middle managers now

"You didn't bring anything to life. You just described how it should be done by the computer using code. The CPU is doing the real work!"

"That is almost to say that the only part of the meal that matters is the cooking. But the cooking is only a tiny part. I take joy in describing the food I want and bringing that vision to life."

It's a bad analogy, because unless you're cooking a recipe, cooking is about all the small decisions you're making during the process which could apply both to coding or the design aspect of building software with an LLM.

What are you trying to say? There are a ton of people who care more about being able to make something they're imagining real than engaging in the process necessary to make it happen. This applies to food just as well as it does to software

Or like going to the gym but using a forklift to lift the weights. Yes, barbells are traveling up and down, but is that the point of going to the gym?

Everyone working in warehouses should stop using forklifts and use their hands like real creatives!

Bad example. This is analogous to people prompting an LLM to "generate code for the sake of it" which of course nobody is doing.

This is timely for me.

Just an hour ago I made my most recent pen plotter generative art free on my website. I plan to send high resolution scans to everyone who joins my mailing list so you can print them at home.

In contrast with the author, I actually enjoy creating code with LLM’s. I’ve been on the technical management track, instead of boots on the ground coding, for quite a few years now. LLMs are letting me produce software again with limited time.

I still enjoy writing code by hand too and my generative art work is mostly that.

https://art.joeldare.com

On the game side, I recently created a Shut the Box game that runs in the web browser. This was created entirely by an LLM. In fact, it was the test project for a Dark Software Factory I’ve built.

I love that I can describe a project, from my phone, put it away, and have a prototype built a few minutes later.

The game is clearly unique and consistent with my own personal style. And, I’m enjoying playing it.

https://dark.joeldare.com/shut-the-box


I once did this by accident and without a bot farm. It was very lucrative.

What I did was create a game with an action button. Then I served ads right next to the action button. I didn’t realize people would miss click on the ads at a high rate, but they did. They fat fingered it, clicked the ad, I got paid.

I looked into it after a couple weeks because my click rate was crazy high.


That's definitely a core principle of crapware that's widely done. Put that ad 0px away from the "mash here like crazy" button, PROFIT!

The back button in Android seems to be a popular one especially when it's only contextually visible on some phones.

My guess is the disks or drive are bad. I have a similar modern Chinese USB 3.5” floppy drive and a box of disks from the 80’s and most of them seem to work fine in that combination.

My research is a few months old, but at the time Vizio looked like the least bad option, largely because a lawsuit had pushed them to narrow what they collect.

Sounds pretty good. Reminds me of the Demo Scene and the types of music they were able to create.

Single html file, ~1000 lines. Love this kind of software.

I want a Qwen 3.8 27B hosted locally but I don't quite have the RAM for it. And, I don't want to buy the RAM until I prove I can use it.

Yesterday I did have success with Gemma-4-12b with 128k context. It fits in my RAM and it's relatively fast on my hardware.

I had to give it prompts that are quite a bit different from the way I use foundation models, but I did get it to work quite well. I feel like I could learn it's differences and get good at using it for real work.


You could try renting a GPU or VPS

Really an aside, but yesterday I got the Gemma-4-12b (128k context) to build it's first web app in the minimal Dark Software Factory I've been building for myself.

https://joeldare.com/a-local-open-weight-model-builds-its-fi...


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: