Re: request for help: LLM-based quality assurance

Collin Funk <[email protected]>
Newsgroups gmane.comp.lib.gnulib.bugs
Message-ID <[email protected]>
Jeffrey Walton <[email protected]> writes:

> I think it is a good idea to utilize LLMs to detect problems,
> especially latent problems that have slipped through the cracks over
> the years.  However, there are downsides to LLMs, and I would look
> into fixing the current processes while using the LLMs as a complement
> to existing practices.

Agreed.

> First, code should not be merged into Master until the CI tests have
> successfully run.  Commits that don't pass the CI test don't pass
> through the security gate.  The new code stays in a development branch
> or testing fork until they pass the CI tests.  This is how many (all?)
> organizations with a mature SDLC operate.

Well, we can't really do that. Our CI is in a separate repository. I
believe this was a decision made by Bruno and Simon because it worked
well previously for them. I do not think this was a consideration at the
time, but I have become a fan of it because it avoids the supply chain
and permission issues that plague "organizations with a mature SDLC"
(see recent happenings associated with TeamPCP).

> Second, LLMs have at least three costs. First is the deskilling that
> happens when relying on them. [1,2]. Relying too much on LLMs will
> have a negative effect on the talent contributing to the project.

I haven't read those particular references, but it is a concern I have.
I think it is a personal responsibility not to offload all your thinking
to an LLM, though.

> Second is the power consumed powering the algorithms, and its effect
> on renewable energy.[3,4] The environmental and societal cost seems to
> be high. Third is the credit system being used to buy LLM time and the
> associated costs.[5] There is no free ride. And if the algorithms are
> going to be invoked at each commit, that could be a disaster at scale.
> Are there enough tokens available to free software to make LLM
> scanning a feasible procedural requirement?

I don't necessarily disagree, but I don't think this argument is very
effective. Everyone knows that eating red meat is terrible for the
environment, but few change their behavior accordingly.

Collin
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.