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/)S

SuspiciousCarrot78

@ SuspiciousCarrot78 @aussie.zone

Posts
20
Comments
340
Joined
4 mo. ago

  • [META] Are paid for, closed source projects, being advertised on this community, appropriate?

    Jump

  • I know your funning / snarking here but...do you know about YaCy?

    https://github.com/yacy/yacy_search_server

    I only learned about it myself a month or so ago and have been thinking about incorporating it into a project of mine (probably overkill - found a more elegant solution) but YaCy sounds like something you might like.

    Also on this topic: I keep seeing meta-crawlers (Degoog, SearXNG, 4get etc) be promoted but...they aren't exactly search engines. They're aggregators that can (and do) get limited. Cool but not "hosting my own search engine" is that was the intent.

  • [META] Are paid for, closed source projects, being advertised on this community, appropriate?

    Jump

  • Partial agreement. My personal stance - it's a bit like porn. Hard to define but I know it when I see it.

    1. first post (ever, anywhere on Lemmy) is an adverting pitch for their brand new project - FAIL
    2. zero effort LLM generated blurb, with no human steering - FAIL
    3. the post is literally an advertisement and adds nothing else - FAIL
    4. the poster does a post and run - FAIL
    5. the post is bot-shaped - FAIL
    6. poster does not / cannot engage with community - FAIL

    The whole thing about paid vs free etc...of course, I prefer FOSS and AGPL, but I don't begrudge anyone trying to recoup costs or keep their source code to themselves. Someone else's software licence shouldn't be a purity test IMESHO

    As for the whole AI / non-AI thing...too much of that comes off as performative. I think we can all spot slop, just like we can all spot email spam. In 2026, I assume you used AI to help...and you can assume (if I am interested in your project) I will use AI to spelunk your code base (initially) for borks, then dive particulars.

  • Removed

    Wrote up a full guide for running AI locally on Windows (LM Studio + Ollama + Open WebUI)

    Jump

  • -236 now. Can it get to -500?

  • Removed

    Wrote up a full guide for running AI locally on Windows (LM Studio + Ollama + Open WebUI)

    Jump
  • Deleted

    Hivekeep - self-host a team of AI agents in one container, with a real UI (MIT)

    Jump

  • Friendly feedback (genuinely) per your request.

    Cardinal sins on Lemmy -

    • First post as self promo
    • AI based project
    • LLM written intro
    • LLM written readme on Github
    • CLAUDE.md et al in repo
    • No disclosure of AI use
    • Commit messages that read like they were done by Claude

    Speaking of, code base itself has "llm wrote this, no one checked" stank.

    I pointed Claude at the first file I could see

    https://github.com/MarlBurroW/hivekeep/blob/main/e2e/01-onboarding.spec.ts

    Issues identified (first 5, trimmed for brevity).

    1. Ghost import (TEST_USER) - classic back-fill residue. Pulled in because it "felt right" alongside the other two helpers, never wired up. No fail-loud catch on it - lint should've flagged it, didn't.
    2. Copy-paste boilerplate x3 instead of beforeEach - pattern got nailed once, then stamped two more times instead of abstracted.
    3. networkidle reflex - slapped after every goto, despite Playwright's own docs actively discouraging that specifically.
    4. Hedge-bet regex (/password/i + filter on /match|mismatch/i). LLM didn't know the exact copy, didn't go check it against source (the grounding step), so it just widened the net to pass either way. Not minding that it hallucinates, in test form.
    5. Comments narrating the line directly below them - zero information gain, pure token filler.

    = you're going to get downvoted to hell because this stinks of AI slop.

    Personally, while Lemmy is militantly FuckAI, I think properly orchestrated, ticketed and reviewed AI code is defensible.

    https://lemmy.ml/post/48724623/26190950

    AI slop (which is sadly what this reads like - please prove us wrong) is going to get kick fucked to death...especially on !selfhosted.

    Not trying to dunk on you...trying to give you a chance to tell us why we should care about this project / install it / what problem it solves.

  • Deleted

    Permanently Deleted

    Jump

  • That came out 25 years ago?

    ...

    Fuck.

  • Deleted

    Permanently Deleted

    Jump

  • Are you asking a technical question or a moral question?

    Pragmatically - IDGAF. If I have it on the ssd, I'll watch it there. If I need to download from torrent or usenet and then watch it, cool. If it's easier to use CloudStream (for some transient series), no problem.

    I tend to keep a corpus of movies / shows on my ssd because it's always there, always reliable, always fast. I have stuff that's just not easy to find online any more and multi-tenancy / bandwidth are no issue. I can throw it in my bag and watch it wherever, even without net.

    It's also agnostic. Not every pirate streaming app works on every device. OTOH, samba share / sftp pretty much does. Tonight I streamed stuff onto a OLPC X-O4...good luck getting fmhy to work with that - it can't even load YouTube directly but stream stuff off the router just fine.

    I don't use JF much any more (prefer ssd plugged directly into router, accessed via NovaPlayer on android devices; files uploaded to via ftp transfer - yes, very 2010) but I think its pretty amazing. Cloudstream and fmhy are amazing too. Use what works.

  • Oops

    Jump

  • Worth pointing out the OAI is US based too. And Mechahitler. And Google. All at the whims of US govt

    Use em if you must (the OAI honeymoon deal - with generous Codex use being included on basic subscription - is hard to beat) but remember...the cloud is someone elses computer...and you especially don't want mission critical shit on someone elses AMERICAN computer.

    OpenCode is probably the best serious cloud competition to the big 4. $10 month.

    Latest versions of GLM, MiMO, Deepseek, Kimi ain't nothing to sneeze at

    https://thomas-wiegold.com/blog/opencode-go-review/

    https://opencode.ai/go

    If someone knows better cloud deal, speak up. Else, local Qwen uber alles.

  • Oops

    Jump

  • So...is this Trump getting back at Darius for refusing to build autonomous weapons? I didn't think he had the attention span.

  • Oops

    Jump

  • They are. But the reputational cost? Who knows.

    Edit: just got an email

    Hello,

    We recently removed access to Claude Fable 5 to ensure compliance with a recent US government directive. Here's a summary of what's happened:

    You no longer have access to Claude Fable 5 You still have access to all other Opus, Sonnet, and Haiku models We reset your usage limits If this change doesn't work for how you use Claude, you can cancel your subscription and get an automatic prorated refund.* To do so, visit this link from a web browser and click “Cancel plan” by Saturday, June 20, 2026, at 11:59 PM PDT (UTC−7). Note that this link will not work in the Claude mobile app. If you subscribed through Apple, please request your refund directly through Apple’s refund support.

    We apologize for the disruption. You can learn more about Anthropic’s response and what led to this decision.

    • Refunds are only available to eligible people who purchased a plan or upgraded their plan between 10:00 AM PDT on June 9, 2026, and 12:00 AM PDT on June 14, 2026 (UTC−7).

    Claude Instagram LinkedIn X Youtube

    Anthropic PBC, 54‌​8 M‌​a‌​r‌​k‌​e‌​t S‌​t, PMB 9‌​0‌​3‌​7‌​5, Sa‌​n F‌​r‌​a‌​n‌​c‌​i‌​s‌​c‌​o, C‌​A 9‌​4‌​1‌​0‌​4

  • I read every day but rarely have my e-reader on me — so I built a self-hosted EPUB library that syncs my reading position between my Kobo and my phone

    Jump

  • Pain. Suffering. Death.

    (I'm kidding...or am I?).

    I always think of home assistant like that scene in V for Vendetta, where he set up an elaborate circle of dominoes, and everything is working perfectly right up until he gets to the last domino.

  • I read every day but rarely have my e-reader on me — so I built a self-hosted EPUB library that syncs my reading position between my Kobo and my phone

    Jump

  • Ah, I thought you meant there was some technical issue that I wasn't aware of / it had been superseded by a superior method.

    Ethical issues aside, the arr stack is a good gateway drug for self hosting. It's fiddly but probably in a useful way. JF/Radarr/Sonarr/Sabnzdb set up genuinely introduces a variety of branching skills.

    Arr leads to self hosting, self hosting leads to home assistant, home assistant leads to ... suffering :)

  • Oops

    Jump

  • Oh, that's weird. My Qwen seems to work just fine 😇

    Kidding aside, I actually had a job I started with Fable the other day - specifically renewed so that I could use it.

    Guess Opus will have to finish it and then I revert to free.

    Truth be told, Fable was nerfed anyway with security theatre.

    Good opportunity for ZAI or someone else to gain some ground.

    No loyalty to cloud shit. They're all cooked. Use what works.

  • I read every day but rarely have my e-reader on me — so I built a self-hosted EPUB library that syncs my reading position between my Kobo and my phone

    Jump

  • Your en dash is showing, Wesley.

  • I read every day but rarely have my e-reader on me — so I built a self-hosted EPUB library that syncs my reading position between my Kobo and my phone

    Jump

  • "A lot" is doing some Olympic level, Gold medal performance lifting there lol.

    Lemmy is loud in its AI hate, nuance be damned. I've seen drivebys on !LocalLLama (notably on a project about AI infinite radio).

    Apparantly, everyone is now an expert on ML and AI (I sure hope they didn't use Gboard or Apple to glide type their message or any sort of STT), just like everyone was an expert on epidemiology, politics, trans rights, ethics, pop culture etc 5 mins ago. You don't need to be an expert to have a position but at the same time, empty cans make the most rattle.

    What's up with arr stack tho? I've been pulling direct from 1337 of late (and even more recently, just using CloudStream). Are we "no one is gay for molemen" on the arr stack?

  • I read every day but rarely have my e-reader on me — so I built a self-hosted EPUB library that syncs my reading position between my Kobo and my phone

    Jump

  • That site appears to look for superficial signals (commit messages, claude.MD file). I wouldn't put too much faith in it for detecting "slop".

    Ironically, the best way to see if something is slop (if a person was so inclined) is to point Claude or ChatGPT at a repo or code example and ask "did a human code this? Why or why not?".

    Unsteered Ai tends to produce immaculate code with logic gaps. Humans tend to produce weird shit that somehow works and actually makes sense when you step back and look at it.

    Probably the best tell is when code clearly bears the marks of "oh, this guy got fucked by this problem; I can see the patch job. It's not elegant but it makes sense if X occurred, which is what Y appears to be for."

    I believe "opinionated" and "belt and suspenders" is the Americanism for that. Kludge and bodge are also true.

    IMHO and YMMV.

  • I read every day but rarely have my e-reader on me — so I built a self-hosted EPUB library that syncs my reading position between my Kobo and my phone

    Jump

  • Genuinely disappointed that didn't lead to a rick roll. Also, did you mean ZnVjayBvZmYgbWF0ZQ==

    Irrespective, good work on the app. It's not something I have personal use for but I salute the effort. You didn't need to make your own personal project public, and you sure as shit didn't need to post it to a hostile site (lemmy has a hate boner for AI something fierce).

    The fact that you did anyway isn't nothing.

    Next time, write more of the intro post yourself :) "What I built" and "I'd love to know..." are too Claude shaped not to rustle jimmies here.

  • I need a map...

    Jump

  • How To Parse JSON Data To A Human Readable Format [SOLVED]

    Jump

  • Perfect. Then my third suggestion stands - get it make you a bespoke training module.

    Create a project container: upload the source documents already cited by others / ones you find useful. Just 4 or 5.

    Add the rule "You are helping me learn ____. You must not provide full refactors unless specifically asked for. Use Socratic method where appropriate".

    Pseudo code what you want to do (hell, draw a flow chart) and ask "based on what I want to do, your background knowledge and the contents of the container, what's the first thing I need to learn? How should I approach this?"

    Then ask "why?"

    Hell, get it to make you coding exercises.

    After each session, get it to make you a handover note in markdown format. Download it and then add that to your container. (Later on, you can get really fancy and start making your own llm-wiki)

    People shit on LLMs as a knee jerk thing... but coding IS a language...and if you understand the logic, the rest is syntax. Also, it's not as if you're making some million dollar mission critical thing- you're teaching yourself through successive approximation.

    If you don't feel comfortable using online models, there are even local alternatives.

    I still think JavaScript is the faster way for this, but who knows.