• 0 Posts
  • 7 Comments
Joined 1 year ago
cake
Cake day: June 11th, 2023

help-circle
  • nefarious@kbin.socialtoProgrammer Humor@programming.devLinux Best Practices
    link
    fedilink
    arrow-up
    92
    arrow-down
    3
    ·
    edit-2
    11 months ago

    Careful, you have to also add --no-preserve-root to make sure you get all of it out. If you leave the roots, it’ll just grow back later!

    (But seriously, don’t actually do this unless you’re prepared to lose data and potentially even brick your computer. Don’t even try it on a VM or a computer you’re planning to wipe anyway, because if something is mounted that you don’t expect, you’ll wipe that too. On older Linux kernels, EFI variables were mounted as writable, so running rm -rf / could actually brick your computer. This shouldn’t still be the case, but I wouldn’t test it, myself.)


  • I don’t trust ChatGPT/GPT-4 for much to begin with, but this study is not great. From Ars Technica’s article on the same topic (with emphasis added by me):

    While this new study may appear like a smoking gun to prove the hunches of the GPT-4 critics, others say not so fast. Princeton computer science professor Arvind Narayanan thinks that its findings don’t conclusively prove a decline in GPT-4’s performance and are potentially consistent with fine-tuning adjustments made by OpenAI. For example, in terms of measuring code generation capabilities, he criticized the study for evaluating the immediacy of the code’s ability to be executed rather than its correctness.

    “The change they report is that the newer GPT-4 adds non-code text to its output. They don’t evaluate the correctness of the code (strange),” he tweeted. “They merely check if the code is directly executable. So the newer model’s attempt to be more helpful counted against it.”

    AI researcher Simon Willison also challenges the paper’s conclusions. “I don’t find it very convincing,” he told Ars. “A decent portion of their criticism involves whether or not code output is wrapped in Markdown backticks or not.” He also finds other problems with the paper’s methodology. “It looks to me like they ran temperature 0.1 for everything,” he said. “It makes the results slightly more deterministic, but very few real-world prompts are run at that temperature, so I don’t think it tells us much about real-world use cases for the models.”