• Things learned from the expeirment (Re: Debian Monthly [debian-devel]:

    From Mo Zhou@21:1/5 to DebGPT on Fri Nov 15 18:30:02 2024
    Hi folks,

    On 11/9/24 01:26, DebGPT wrote:
    This is an experiment, by letting LLM go through all 369 emails from debian-devel on Oct.

    I received lots of feedbacks from the experiments, from positive ones
    to negative ones. It wasn't discouraging to see negative feedbacks since
    that is usually what would happen when people see something that has
    not appeared in the past. However, I see the core value of this experiment
    as the opportunity that the community and I can learn from it.

    Speaking of AI summary in the context of Debian community, I think it
    brings more harm than benefit if broadcasted to general audience --
    unless the industry can realiably address the hallucination issues.
    While AI summary might be helpful to some extent, it in fact requires
    a certain level of expertise from the user, in order to properly tell
    its good parts and bad parts, and make use of its good parts. However,
    assuming a public general audience with such expertise (or at least
    tolerance) is not practical -- there might be people who consume the
    bad parts as well along with the good. We simply cannot bear the cost
    of forcing people to learn to tell the truth and the hallucinations.

    Whenever the community needs to face more interaction with AIs, this
    experiment can serve as an example for precaution.


    Apart from that, I'll continue trying to explore the ways to make such
    new technology useful since I'm interested in it. I can leak some of
    my plans in this regard:

    1. Let LLM answer the NM templates (maybe with debian policy or debian developer reference in context) and see the percentage of questions
    that can be answered correctly. Even if I don't do it, maybe new DD
    applicants will.

    2. Continue adding features to DebGPT and make a major release.

    Since the first time when DebGPT was announced, I wrote many new stuff to
    this tool -- and it gradually became my daily terminal LLM tool (I cannot
    find a better one on pypi).

    One of the interesting features is to edit file inplace, automatically
    git add, generate git message and commit. This has been very reliable and useful for simple tasks like adding documentation and type annotations
    in DebGPT's python code. Really saves lots of time.

    An real example for the described fully automated pipeline: https://salsa.debian.org/deeplearning-team/debgpt/-/commit/4735b38141eafd6aa9b0863fc73296aa41562aed
    What I did is just type the instruction in natural language, then the implementation is automatically committed in git.

    For me that's a fun part.

    --- SoupGate-Win32 v1.05
    * Origin: fsxNet Usenet Gateway (21:1/5)
  • From Charles Plessy@21:1/5 to All on Sat Nov 16 03:40:01 2024
    Hi Mo,

    thanks again for your posts,

    I was just thinking that the debian-mentors list could be a good target
    for summarisation too: it is high traffic, email subject lines are
    focused on what to upload, but discussions are focused on
    problem-solving, thus some intersting tips & trick will be easy to miss
    by people who do not read everything.

    (Maybe also you can ask in the propmpt to avoid reporting people names
    for the moment?)

    Have a nice week-end,

    Charles

    --- SoupGate-Win32 v1.05
    * Origin: fsxNet Usenet Gateway (21:1/5)
  • From Joerg Jaspert@21:1/5 to Mo Zhou on Sat Nov 16 14:30:01 2024
    On 17414 March 1977, Mo Zhou wrote:

    1. Let LLM answer the NM templates (maybe with debian policy or debian developer reference in context) and see the percentage of questions
    that can be answered correctly. Even if I don't do it, maybe new DD applicants will.

    And those who actually do this should, if we catch them, NOT ever end up
    a DD. So I hope noone is as stupid.

    --
    bye, Joerg

    --- SoupGate-Win32 v1.05
    * Origin: fsxNet Usenet Gateway (21:1/5)