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/)U

unfortunate_ferret

@ obelisk_complex @piefed.ca

Posts
4
Comments
118
Joined
6 mo. ago

  • Mastodon.world cancels famous German author Kazim's posts - now he left Mastodon completely

    Jump

  • I think that there's a specific kind of person who responds to a tragic event by looking for and reporting on people celebrating the tragedy. In my several decades of experience, the point always seems to be to try and vilify the people who share a few traits like skin colour, language, or ethnicity, and somehow it's always a group the "reporter" has some kind of problem with.

    Trump did the same thing after 9/11, you know. Do you support that Trumpy kind of behaviour, to try and incite hatred against particular groups of people in that manner?

  • Leavitt previews Trump’s primetime speech: Election ‘adjustments’ coming

    Jump

  • Open source is a thankless job and I think we've lost the plot on how we treat maintainers

    Jump

  • Guy keeps talking about their "customers" and they don't charge a dime. I'm not sure that word means what he thinks it means. They have users, and that's exactly what he's acting like.

  • Are there any websites from the 90s that you can remember but can find no trace of now?

    Jump

  • Early 2000s: The Mech Madness forums, for discussing Armored Core, BattleTech, Gundam, and all other things mech and mech-related. It was a decent-sized community, for the time.

  • Top Democrat seems sour after Mamdani-backed candidates oust House incumbents

    Jump

  • I appreciate that you picked up what I was putting down. So little room for artistry in written communication, nowadays.

  • Top Democrat seems sour after Mamdani-backed candidates oust House incumbents

    Jump

  • They are strategists prioritizing their own wants above that of the voters and human decency

    Right, that's what we said. Cowards.

  • Thoughts on Hermes?

    Jump

  • Any time, I hope they're helpful! (☞ﾟヮﾟ)☞

    I’m a little surprised to hear you say PAYG for Opus sub agents is economical

    I did say it was surprising! 😂 To give you an idea what I mean by "economical", it's never more than a few bucks a day, even on days of heavy use and development with "loop until clean" instructions on QA (for which I use Opus). I accidentally blew through my opencode go quota really early in the first month, so I ended up on PAYG; here's the usage graph:

    And here's the numbers breakdown for the highest day (I was evaluating GLM5.1 for general tasks - don't use it for that, it's really token hungry)

    That includes a lot of experimentation too while I figured out which models were best for what. I hid Fable because it crushed the rest of the table - really expensive, but worth it for one-shotting very long tasks on the Anthropic subscription is what I found.

  • Thoughts on Hermes?

    Jump

  • The harness helps a lot even with local models. In fact, I just found this this morning and cherrypicked it: https://github.com/DietrichGebert/ponytail

    Recommend doing the same, and for superpowers if you don't have 'em already: https://github.com/obra/superpowers

    Opencode Go is the $10/month cloud model subscription from the same group maintaining the OpenCode software. Opencode Zen is a pay-as-you-go version which gives you access to Claude models as well. Keeping pay-as-you-go to subagents only (e.g. telling your agent to launch an opus subagent via your opencode zen key) is actually surprisingly economical - when you're not going turn after turn with hundreds of thousands of tokens of context, claude is pretty reasonably priced.

    What I'm doing is spreading out my usage over multiple cheap subscriptions, and augmenting with the occasional pay-as-you-go frontier agent, to get quality in line with what you get out of Claude, at usage that would require the $200/month level, for a lot less money than that.

  • Thoughts on Hermes?

    Jump

  • I've been using it with Opencode Go, Ollama, and Claude Code (it can delegate tasks to models through all those, so you can have Claude plan and Deepseek Flash build); I really like it.

    I ran into that problem with the agent reporting that subagents succeeded, or work had been done, where it hadn't ("I said I tested that, but I didn't. That's on me. Won't happen again"), so I built a self-check enforcement system for it. You or your agent can set up the system by reading this: https://github.com/obelisk-complex/hermes-agent/blob/main/self-check-enforcement-system-v15.md

    It includes the source patch which adds a hook on_output; this allows you to intercept text sent directly from the LLM to the user, which in vanilla is unblockable. So, this system ensures that if something remains unfinished, the LLM can't say it's done; it has to acknowledge what it didn't do before it can send you a message to close the conversation loop. I've built the fork to automatically merge upstream changes around this patch daily at 0400 Pacific time, so I should stay up to date (ish).

    I also put in a feature request to get this added upstream. Feature request here: https://github.com/NousResearch/hermes-agent/issues/45881

  • Deleted

    Permanently Deleted

    Jump

  • I typically prefer subbed; watching dubbed feels off somehow. Then again, I'm perfectly fine with the dubbing in DBZA so it must be a preference I learned somewhere!

  • Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code

    Jump

  • If you want the FOSS community to be there for you, don't go out of your way to use the corporate BS that's actively destroying it.

    Heheh, and another one of you thought to call me hyperbolic.

  • Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code

    Jump

  • intentionally designed to cause disruption to a computer, server, client, or computer network

    Actively and deliberately adding text with the explicit purpose of attempting to delete other peoples' work fits this quite nicely, thank you for including it to illustrate my point.

  • Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code

    Jump

  • Someone actively trying to sabotage their users is not okay, regardless of the excuses you want to trot out.

  • Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code

    Jump

  • I'll try to make my point clearer:

    Damaging other people's shit because you don't like the way they live is not okay.

  • Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code

    Jump

  • I don't see how that's relevant here. Banksy didn't then go and shred every other piece of art the buyer owned. That would be pretty fucked up.

  • Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code

    Jump

  • I appreciate you seeing this for what it is and saying so, where other people are twisting themselves into pretzels to pretend like it's anything else.

  • Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code

    Jump

  • Classy.

  • Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code

    Jump

  • Yeah, I don't care what their reasons are, they added malware to their own project to fuck over a portion of their user base. That's not okay.

    Let's analogise: an artist discovers their art has been printed out and hung on the wall in the home of someone they don't like. Does that artist have the right to try and burn down that person's house in retribution?

  • Introducing Claude Opus 4.8

    Jump

  • Ahhhh fair play. I have a lot of freedom since I'm paying out of pocket for my own use. I have a pretty beefy rig for running local, but it's not beefy enough to run deepseek pro and the like 😬 so, I have a bunch of subscriptions to try out a bunch of different models and see what works best in my workflow. I also have a problem with making alts in games, which seems like it rhymes 🤔

    Been pretty impressed with glm5.1 too, before deepseek-v4 came out, but you'd be amazed what even a smaller older coding model can do with the right config and a little proactive context management. I really hope this trend of smaller, better models for local agentic use continues.

  • Selfhosted @lemmy.world
    unfortunate_ferret @piefed.ca

    Updated: Honey, I Shrunk The Vids 2.3.4

    github.com /obelisk-complex/histv-universal
  • Selfhosted @lemmy.world
    unfortunate_ferret @piefed.ca

    Honey, I Shrunk The Vids v2.1.2 - Now in CLI flavour!

    github.com /obelisk-complex/histv-universal
  • Selfhosted @lemmy.world
    unfortunate_ferret @piefed.ca

    Honey, I Shrunk The Vids [Mr. Universe Edition] v1.0.9

    github.com /obelisk-complex/histv-universal
  • Selfhosted @lemmy.world
    unfortunate_ferret @piefed.ca

    Honey, I Shrunk The Vids - a Windows transcoding frontend for FFMPEG

    codeberg.org /dorkian_gray/histv