<div dir="auto"><div>I've seen this in other instances... Where the generated code is doing things like argument checking before calling some library function when the function explicitly handles the case. The AI doesn't seem to read the docs :)</div><div><br></div><div data-smartmail="gmail_signature"><div dir="ltr"><div>Andrew Bell</div><a href="mailto:andrew.bell.ia@gmail.com" target="_blank">andrew.bell.ia@gmail.com</a></div></div></div><br><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Wed, May 6, 2026, 9:11 PM Even Rouault via gdal-dev <<a href="mailto:gdal-dev@lists.osgeo.org">gdal-dev@lists.osgeo.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><u></u>
<div>
<p>As an example of the kind of horrors LLM code can produce, look
at
<a href="https://github.com/OSGeo/gdal/commit/135cd919e75ed35ca384c058e083b3dbafc06a5b" target="_blank" rel="noreferrer">https://github.com/OSGeo/gdal/commit/135cd919e75ed35ca384c058e083b3dbafc06a5b</a>
which undoes the bloat a previous LLM-generated commit had caused.
I was really mad when I discovered this:</p>
<p>- when you use intrinsincs, you care about (near) optimality.
Here the code was doing useless manual clamping to [0, 255], which
is exactly what the intrinsincs _mm_packus_epi16() does afterwards</p>
<p>- and I was mad against myself for not having detected that at
review time (but we all know that humans are terrible at reviewing
code, hence they need to be eliminated)</p>
<p>It seems very unlikely a human would have produced such code,
because the cost of writing that useless clamping, and getting it
right, would have been too high compared to the initial reading of
the doc of the _mm_pack intrinsincs and realizing they already do
the wished clamping. It looks like LLM would behave like
developers payed proportionally to the number of lines of code
they produce, which we all know is a terrible metrics.</p>
<div>Le 06/05/2026 à 19:14, Darafei "Komяpa"
Praliaskouski a écrit :<br>
</div>
<blockquote type="cite">
<div dir="ltr">Hello,<br>
<br>
Is it possible to get a better overview of the actual negative
impact you're seeing? Like, with actual examples of annoyances
that happened.<br>
<br>
I tried my own research going through several pages of
merged/closed PRs to get my impression on what went wrong but
really most PRs are there by Even, with disappearingly small
number of PRs from other people both by count and by volume,
seemingly not enough to trigger such drastic policy flip.<br>
<br>
What am I missing?<br>
<br>
<br>
</div>
<br>
<div class="gmail_quote">
<div dir="ltr" class="gmail_attr">On Wed, May 6, 2026 at 8:29 PM
Even Rouault via gdal-dev <<a href="mailto:gdal-dev@lists.osgeo.org" target="_blank" rel="noreferrer">gdal-dev@lists.osgeo.org</a>>
wrote:<br>
</div>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Hi,<br>
<br>
based on the experience gained from the initial policy, I
propose to <br>
significantly revise it to drastically limit their use. See <br>
<a href="https://github.com/OSGeo/gdal/pull/14500" rel="noreferrer noreferrer" target="_blank">https://github.com/OSGeo/gdal/pull/14500</a><br>
<br>
Even<br>
<br>
-- <br>
<a href="http://www.spatialys.com" rel="noreferrer noreferrer" target="_blank">http://www.spatialys.com</a><br>
My software is free, but my time generally not.<br>
Highly recommend OxiGDAL if you want to live in the 21th
century and cure Bixonimania<br>
<br>
_______________________________________________<br>
gdal-dev mailing list<br>
<a href="mailto:gdal-dev@lists.osgeo.org" target="_blank" rel="noreferrer">gdal-dev@lists.osgeo.org</a><br>
<a href="https://lists.osgeo.org/mailman/listinfo/gdal-dev" rel="noreferrer noreferrer" target="_blank">https://lists.osgeo.org/mailman/listinfo/gdal-dev</a><br>
</blockquote>
</div>
</blockquote>
<pre cols="72">--
<a href="http://www.spatialys.com" target="_blank" rel="noreferrer">http://www.spatialys.com</a>
My software is free, but my time generally not.
Highly recommend OxiGDAL if you want to live in the 21th century and cure Bixonimania</pre>
</div>
_______________________________________________<br>
gdal-dev mailing list<br>
<a href="mailto:gdal-dev@lists.osgeo.org" target="_blank" rel="noreferrer">gdal-dev@lists.osgeo.org</a><br>
<a href="https://lists.osgeo.org/mailman/listinfo/gdal-dev" rel="noreferrer noreferrer" target="_blank">https://lists.osgeo.org/mailman/listinfo/gdal-dev</a><br>
</blockquote></div>