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/)A
Posts
18
Comments
778
Joined
3 yr. ago

FLOSS virtualization hacker, occasional brewer

  • The most useful use case for me is querying a knowledge base in NotebookLM. I work on CPU emulation and it does a very good job of extracting the relevant information from thousands of pages of dry technical specs and preparing the requirements for implementing a particular feature.

    The Deep Research mode of Gemini is pretty good at generating some briefing notes (with links) and can do that in the background once you kick it off.

  • On the potentially bright side maybe this will make people think harder about which model to use for which task. You don't need to feed your entire code base into Opus when a Gemini Flash sub-agent can do a perfectly fine job running grep and compiling a summary for the main agent.

  • After the sequel it's usually diminishing returns for the plot.

  • Even Debian has popcon as an opt in. I can see why collecting data about hardware and package choices is useful to Ubuntu. I didn't think they collected any personally identifying information.

  • Was he inverted?

  • I also have a diverter which heats up my hot water tank which saves on gas, especially in the summer.

  • It will be fun watching those users who first make the jump to the new project.

  • Export to the grid, for every kWh I export during the day I can afford two kWh overnight.

  • If it's finding valid vulnerabilities then it's just another tool like static analysis, fuzzers and sanitizers. There definitely seems to be a difference in quality compared to earlier generations that were behind the sloppy avalanch of reports.

  • Funny 😂

  • I think the article is over complicating things. I work in a project which is heavily forked for a variety of reasons. While it's academically interesting to look at the reasons for those downstream forks we have no interest in going to the considerable effort of tracking them all.

    If you can take a project and use an LLM to enable your niche use case then more power to you. FLOSS was never about ensuring all patches flow upstream.

  • They don't have to be. They know what they asked the LLM to do. They know how much they adapted the output. You usually have to work to get the models to spit out significant chunks of memorised text.

  • No, that's why the author asserts that with their signed-of-by. It's what I do if I use any LLM content as the basis of my patches.

  • If the 2-10% is just boilerplate syscall number defines or trivial MIN/MAX macros then it's just the common way to do things.

  • If you are using MakeMKV when ripping you can override the filename template. So I name them for example "Show s01e04+" based on the disc I'm ripping. Then once encoded it's relatively quick to rename the files with the full episode number. I personally use dired in Emacs because a macro makes short work of the renaming but I'm sure other solutions are possible.

  • My Bravia experience improved markedly when I replaced Sony's default home screen with the Projecivity Launcher.

  • Where are you seeing the 2-10% figure?

    In my experience code generation is most affected by the local context (i.e. the codebase you are working on). On top of that a lot of code is purely mechanical - code generally has to have a degree of novelty to be protected by copyright.

  • I was glad to see Niko publish his initial work and look forward to seeing how it's gone.

  • Electric Vehicles @slrpnk.net

    Why it has not been so easy being green for the white van in the UK

    www.theguardian.com /environment/2026/jan/24/electric-van-fleets-uk
  • LocalLLaMA @sh.itjust.works

    Overview - ECA - Editor Code Assistant

    eca.dev
  • UK Politics @feddit.uk

    Parents threatened by authorities as 1,000 adopted children returned to care

    www.bbc.co.uk /news/articles/c0kdv1x83gko
  • Videos @lemmy.world

    This Autism stat makes no sense

  • Virt-Manager @programming.dev

    QEMU version 10.0.0 released - QEMU

    www.qemu.org /2025/04/23/qemu-10-0-0/
  • UK Politics @feddit.uk

    Why the Post Office paid £600m to stay shackled to the faulty Horizon system

    www.bbc.com /news/articles/cgm8lmz1xk1o
  • Open Source @lemmy.ml

    QEMU version 10.0.0 released

    www.qemu.org /2025/04/23/qemu-10-0-0/
  • Free Software @lemmy.zip

    QEMU version 10.0.0 released

    www.qemu.org /2025/04/23/qemu-10-0-0/
  • homeassistant @lemmy.world

    Can't add matter devices with f-droid companion app

  • No Stupid Questions @lemmy.world

    What ever happened to QAnon?

  • Open Source @lemmy.ml

    Fish 4.0: The Fish Of Theseus

    fishshell.com /blog/rustport/
  • UK Politics @feddit.uk

    Hilary Cass: Weak evidence letting down children in gender care

    www.bbc.co.uk /news/health-68770641
  • Programmer Humor @lemmy.ml

    infosec.exchange /users/mainframed767/statuses/112180749990584294
  • Programmer Humor @lemmy.ml

    A week of fprintfs has me wanting to code rust next week

  • homeassistant @lemmy.world

    Controllable water valves?

  • LocalLLaMA @sh.itjust.works

    How to make LLMs go fast

    vgel.me /posts/faster-inference/
  • LocalLLaMA @sh.itjust.works

    A Systems Programmer's Perspectives on Generative AI

    www.bennee.com /~alex/blog/2023/12/10/a-systems-programmers-perspectives-on-generative-ai/
  • UK Politics @feddit.uk

    The Rest Is Politics: 179 discussing the dangers of deep fakes.

    traffic.megaphone.fm /GLT8781805084.mp3