It's refreshing to see a well-argued and balanced essay on AI risk being upvoted on Hacker News.

It looks like like the link shortener vanderbi.lt, operated by Vanderbilt University, was compromised in some form, too: https://fi-le.net/vanderbilt

Yep, some of them still show up indexed in Google if you do 'site:vanderbi.lt' - a few of them seem to be accessed after the main event that's documented here. May just be someone researching/ reproducing? This is fascinating though.

If you read the article, you'll find that, surprisingly, the delay I was personally observing likely has nothing to do with AI-assisted submissions.

“And here we found the culprit. The paper I was submitting belongs under cs.CY, Computers and Society, as I now know after reviewing all the categories more carefully.” I’d think the indirect cause is ai, given its recent bull/glass shop approach.

Within the cs.CY category, I only found a slight increase in delays since 2016, that seems to be well within error bars, but it could also be that my sample size was too small.

fi-le.net

Thank you for the nitpick, corrected!

Thank you, corrected!

Thank you for the kind words.

Thank you! As the other commenters already figured out, I manually write HTML and use tufte.css with some minor customizations.

What percentage, in numbers?

Evals for programming languages with formal verification. It's not clear how far we are from good coding performance in less popular languages in general, and formal verification has some quirks on top also.