Re: scary patch contest

On Fri, Aug 28, 2026 at 4:35 PM Zsolt Parragi <zsolt(dot)parragi(at)percona(dot)com> wrote:
>
> On Fri, 28 Aug 2026, Xuneng Zhou <xunengzhou(at)gmail(dot)com> wrote:
> > Interestingly, although the current SOTA model can do good things
> > without complicated prompts, it still seems useful for complicated
> > tasks. Here's a prompt that I plan to give Sol a try.
>
> I'm running something very similar with Fable, also focusing on the
> prioritization / restartability as it eats up usage limits quickly. It
> already ran ~30% of the planned first-round checks, and reported 22
> issues with reproducers so far. Running it with another model seems
> like a good idea, most likely while they will have common discoveries,
> some of the findings will be different.

It refused to show the results due to some cyber security concerns
after burning some tokens... Maybe only members of Guardians of the
Database Galaxy are allowed to see it. So counting on yours.

--
Regards,
Xuneng Zhou
HighGo Software Co., Ltd.