Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)P

pyr0ball

@ pyr0ball @reddthat.com

Posts
1
Comments
16
Joined
3 yr. ago

  • Removed Locked

    Most slopcode projects are abandoned and deleted within months of release

    Jump

  • Also, fair warning: my day job involves writing docs and reports for corporate clients, so the LinkedIn voice leaks in whether I want it to or not. Working on it.

  • Removed Locked

    Most slopcode projects are abandoned and deleted within months of release

    Jump

  • Ha, the irony isn't lost on me. But the comment was mine, not generated. The project does use LLMs as a tool (that's the point of it), but "uses LLMs" and "is slop" aren't the same thing. The repo is public if you want to check the commit history and structure rather than take my word for it.

  • Removed Locked

    Most slopcode projects are abandoned and deleted within months of release

    Jump

  • Fair point, I'll own it. Dropping a project link in a thread about slopcode is going to read as a pitch, and I needed to promote or nothing will ever happen.

    That said, I figured showing a concrete example was more useful than just adding another opinion to the pile. If you want to pull the repo (https://git.opensourcesolarpunk.com/Circuit-Forge/peregrine), the structure is there to review. There's a deterministic pipeline underneath the LLM layer (eligibility checks, form validation, deadline tracking all run without LLM involvement), CI with test coverage, and a fine-tuned model approach that keeps inference on local hardware where possible.

    The hard part wasn't the LLM layer, it was the plumbing around it that keeps the LLM in an advisory role instead of a decision-making one. That design constraint is what I wanted to show, not just "look, I made a thing."

  • Removed Locked

    Most slopcode projects are abandoned and deleted within months of release

    Jump

  • The pre-LLM-effort-was-a-filter argument holds up, but I think what effort was really filtering for was why someone built the thing. High effort filtered out "this seemed fun for a weekend" projects. LLMs just surfaced that those were always the majority.

    The better filter is: does this project serve a specific audience that genuinely needs it, or is it a demo of what you can do with Claude?

    What I look for now:

    • Specific problem for a specific group of people (not "general-purpose LLM wrapper")
    • Open core (MIT or something that lets the community carry it if the author walks)
    • Revenue model or institutional backing (someone has to keep the lights on)
    • Evidence the author understands what they shipped, not just LLM output committed wholesale

    We build CircuitForge, self-hosted tools for navigating opaque systems (job markets, government benefits, insurance). The architecture is deterministic-first: eligibility checks, validation, and data pipelines are rule-based and grounded in structured data, so the LLM is drafting from a clean, repeatable foundation rather than hallucinating into a void. That also means we can run smaller, specifically fine-tuned models instead of throwing a frontier model at everything and hoping for the best. Smaller models run on consumer hardware, which cuts hosting cost and shrinks the privacy risk surface significantly. Humans approve before anything acts. Pipeline layer is MIT and lives on Forgejo. There's a full devops stack, a real business model, and I use these tools every day. We're also actively collaborating with other devs and always looking for contributors.

    The people using these tools actually need them. That's the commitment signal that doesn't evaporate when the novelty wears off.

  • Zo Computer

    Jump

  • Own nothing.... Rent everything!

    /s

  • US Supreme Court just blew up EU-US Data Transfers

    Jump

  • Search for "Thiel Dialogue Leaks" for more nightmare fuel to read

  • 🤔 Interesting

    Jump

  • You clearly didn't read very far, but I guess I need to be more upfront about the details. The only thing I charge for is using my hardware, and I'm only doing that for people who can't do it for themselves. All of the software is open source. All of the software is self-hostable, and the three I built first don't even need an LLM to be useful. I'm building it with low-spec (8gb vram or less) as the priority deployment option so anyone who is capable can use these for free

    I'm one engineer trying to democratize and federate AI

  • 🤔 Interesting

    Jump

  • 🤔 Interesting

    Jump

  • Your brain was never designed for this much bad news

    Jump

  • Happy to help!

  • Your brain was never designed for this much bad news

    Jump

  • You're depleted and need time to recover before you try helping again. This is a perfect case of "secure your own mask before assisting others".

    Go be with friends. Touch some grass. Do some art. Go visit a garden or plant something.

    If you feel up to it, look into volunteering we local food banks or animal shelters.

    On a larger scale, build a digital lifeboat and de-google/apple/fb. Form privacy cooperatives with your family and friends (whoever is the techiest runs a server for the cooperative and you all share a private cloud). This can act as a filter and a support group if managed well.

  • Hillary Clinton: Biden reelection campaign a ‘terrible mistake’

    Jump

  • At least that still has the option of circumvention without the massive loss of life and suffering we've seen across the world as a result of the instability introduced into would politics by Trumpism, but sure... This is fine...

  • Removed

    What do you call this type of scifi? Could you also recommend some fiction with this vibe?

    Jump

  • Stephen Baxter has a ton of hard sci fi books with a similar aesthetic, expansive stories, and interesting philosophy

  • Discarr: disc rip → Sonarr/Radarr pipeline, no npm deps [GPL-3.0]

    Jump

  • Ah, well you see the explanation for that is pure ignorance. I've only ever used handbrake myself and was trying to help another friend who apparently uses makeMKV wrong or something or is bad at explaining to me xD

  • Discarr: disc rip → Sonarr/Radarr pipeline, no npm deps [GPL-3.0]

    Jump

  • Sure, but that takes a lot of time and effort when you have a complicated stack, so it's nice to be able to handle it in two clicks instead of setting up an entire encode queue while cross referencing all my metadata so I get episodes mapped right. Often a series session will take me upward of 30 minutes to set up an encode queue manually. With Discarr, it takes me 30 seconds

    Edit: this came out of many attempts to create a single script that could post-process torrents, unpacking archives or converting disk images dynamically. The trouble is that dvd formatting for series follows no standards whatsoever, and really requires a human to map the titles. Discarr automates everything except that, and surfaces the title and episode queues side-by-side to allow quick identification and assignment

  • Discarr: disc rip → Sonarr/Radarr pipeline, no npm deps [GPL-3.0]

    Jump

  • Sonarr/Radarr occasionally grab disk rips as they're the only format available for certain titles, but they can't be directly imported without conversion. This fills that gap cleanly.

  • Selfhosted @lemmy.world
    pyr0ball @reddthat.com
    GPL-3.0

    Discarr: disc rip → Sonarr/Radarr pipeline, no npm deps

    git.opensourcesolarpunk.com /Circuit-Forge/discarr