MIME-Version: 1.0
References: <CAKAnmm+tbPMdP8ccrJ-o_LVgC6ADdOEoh2=J+zyWNLab6B3+_Q@mail.gmail.com>
In-Reply-To: <CAKAnmm+tbPMdP8ccrJ-o_LVgC6ADdOEoh2=J+zyWNLab6B3+_Q@mail.gmail.com>
From: Kashif Zeeshan <kashi.zeeshan@gmail.com>
Date: Wed, 17 Jul 2024 22:43:33 +0500
Message-ID: <CAAPsdhdBTgQpG1VAfGVmT9kZmRLLdsxYrLhX-DFNmpM-CDyhrA@mail.gmail.com>
Subject: Re: Planet Postgres and the curse of AI
To: Greg Sabino Mullane <htamfids@gmail.com>
Cc: pgsql-general <pgsql-general@lists.postgresql.org>
Content-Type: multipart/alternative; boundary="000000000000d12c8d061d750016"
Archived-At: <https://www.postgresql.org/message-id/CAAPsdhdBTgQpG1VAfGVmT9kZmRLLdsxYrLhX-DFNmpM-CDyhrA%40mail.gmail.com>
Precedence: bulk

--000000000000d12c8d061d750016
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

Hi Greg

I agree with you on the misuse of AI based tools, as per my experience with
Postgres the solutions suggested wont work at times.
Its not bad to get help from these tools but put all the solutions from
there is counter productive.
I think People should take care while using these tools while suggesting
solutions for real world problems.

Regards
Kashif Zeeshan

On Wed, Jul 17, 2024 at 10:22=E2=80=AFPM Greg Sabino Mullane <htamfids@gmai=
l.com>
wrote:

> I've been noticing a growing trend of blog posts written mostly, if not
> entirely, with AI (aka LLMs, ChatGPT, etc.). I'm not sure where to raise
> this issue. I considered a blog post, but this mailing list seemed a bett=
er
> forum to generate a discussion.
>
> The problem is two-fold as I see it.
>
> First, there is the issue of people trying to game the system by churning
> out content that is not theirs, but was written by a LLM. I'm not going t=
o
> name specific posts, but after a while it gets easy to recognize things
> that are written mostly by AI.
>
> These blog posts are usually generic, describing some part of Postgres
> in an impersonal, mid-level way. Most of the time the facts are not
> wrong, per se, but they lack nuances that a real DBA would bring to the
> discussion, and often leave important things out. Code examples are often
> wrong in subtle ways. Places where you might expect a deeper discussion a=
re
> glossed over.
>
> So this first problem is that it is polluting the Postgres blogs with
> overly bland, moderately helpful posts that are not written by a human, a=
nd
> do not really bring anything interesting to the table. There is a place f=
or
> posts that describe basic Postgres features, but the ones written by huma=
ns
> are much better. (yeah, yeah, "for now" and all hail our AI overlords in
> the future).
>
> The second problem is worse, in that LLMs are not merely gathering
> information, but have the ability to synthesize new conclusions and facts=
.
> In short, they can lie. Or hallucinate. However you want to call it, it's=
 a
> side effect of the way LLMs work. In a technical field like Postgres, thi=
s
> can be a very bad thing. I don't know how widespread this is, but I was
> tipped off about this over a year ago when I came across a blog suggestin=
g
> using the "max_toast_size configuration parameter". For those not
> familiar, I can assure you that Postgres does not have, nor will likely
> ever have, a GUC with that name.
>
> As anyone who has spoken with ChatGPT knows, getting small important
> details correct is not its forte. I love ChatGPT and actually use it dail=
y.
> It is amazing at doing certain tasks. But writing blog posts should not b=
e
> one of them.
>
> Do we need a policy or a guideline for Planet Postgres? I don't know. It
> can be a gray line. Obviously spelling and grammar checking is quite
> okay, and making up random GUCs is not, but the middle bit is very hazy.
> (Human) thoughts welcome.
>
> Cheers,
> Greg
>
>

--000000000000d12c8d061d750016
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">Hi Greg<div><br></div><div>I agree with you on the misuse =
of AI based tools, as per my experience with Postgres the solutions suggest=
ed wont work at times.</div><div>Its not bad to get help from these tools b=
ut put all the solutions from there is counter productive.</div><div>I thin=
k People should take care while using these tools while suggesting solution=
s for real world problems.</div><div><br></div><div>Regards</div><div>Kashi=
f Zeeshan</div></div><br><div class=3D"gmail_quote"><div dir=3D"ltr" class=
=3D"gmail_attr">On Wed, Jul 17, 2024 at 10:22=E2=80=AFPM Greg Sabino Mullan=
e &lt;<a href=3D"mailto:htamfids@gmail.com">htamfids@gmail.com</a>&gt; wrot=
e:<br></div><blockquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0=
.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir=3D"l=
tr"><div class=3D"gmail_quote"><div dir=3D"ltr">I&#39;ve been noticing a gr=
owing trend of blog posts written mostly, if not entirely,=C2=A0with AI (ak=
a LLMs, ChatGPT, etc.). I&#39;m not sure where to raise this issue.=C2=A0I =
considered a blog post, but this mailing list seemed a better forum to=C2=
=A0generate a discussion.<br><br>The problem is two-fold as I see it.<br><b=
r>First, there is the issue of people trying to game the system by churning=
 out=C2=A0content that is not theirs, but was written by a LLM. I&#39;m not=
 going to name=C2=A0specific posts, but after a while it gets easy to recog=
nize things that=C2=A0are written mostly by AI.<br><br>These blog posts are=
 usually generic, describing some part of Postgres in=C2=A0an impersonal, m=
id-level way. Most of the time=C2=A0the facts are not wrong,=C2=A0per se, b=
ut they lack nuances that a real DBA would bring to the discussion,=C2=A0an=
d often leave important things out. Code examples are often wrong in subtle=
 ways. Places where you might expect a deeper discussion are glossed over.<=
/div><div dir=3D"ltr"><br></div><div dir=3D"ltr">So this first problem is t=
hat it is polluting the Postgres blogs with overly=C2=A0bland, moderately h=
elpful posts that are not written by a human, and do not=C2=A0really bring =
anything interesting to the table. There is a place for posts=C2=A0that des=
cribe basic Postgres features, but the ones written by humans are=C2=A0much=
 better. (yeah, yeah, &quot;for now&quot; and all hail our AI overlords in =
the future).<br><br>The second problem is worse, in that LLMs are not merel=
y gathering information,=C2=A0but have the ability to synthesize new conclu=
sions and facts. In short, they can lie.=C2=A0Or hallucinate. However you w=
ant to call it, it&#39;s a side effect of the way LLMs work. In a technical=
=C2=A0field like Postgres, this can be a very bad thing. I don&#39;t know h=
ow widespread this=C2=A0is, but I was tipped off about this over a year ago=
 when I came across a blog=C2=A0suggesting using the &quot;max_toast_size c=
onfiguration parameter&quot;. For those not familiar,=C2=A0I can assure you=
 that Postgres does not have, nor will likely ever have, a GUC with that na=
me.<br><br>As anyone who has spoken with ChatGPT knows, getting small impor=
tant details=C2=A0correct is not its forte. I love ChatGPT and actually use=
 it daily. It is=C2=A0amazing at doing certain tasks. But writing blog post=
s should not be one of them.<br><br>Do we need a policy or a guideline for =
Planet Postgres? I don&#39;t know.=C2=A0It can be a gray line. Obviously sp=
elling and grammar checking is quite okay,=C2=A0and making up random GUCs i=
s not, but the middle bit is very hazy. (Human) thoughts welcome.<br></div>=
<div dir=3D"ltr"><br></div><div>Cheers,</div><div>Greg</div><div><br></div>=
</div></div>
</blockquote></div>

--000000000000d12c8d061d750016--