But err, don't let that stop you, Space Hobo! I'm not sure how anyone is taking this Mastodon post seriously. The author barely knows Tridgell, but is supposedly 'concerned' because he hasn't posted to his local LUG mailing list for a few years. Isn't this the logic of the terminally online?

I notice that Space Hobo has a lot of posts warning about the dangers of AI slop. Given the rate at which they're able to produce copious quantities of their own artisanal variety, I can't imagine they have much to fear.

It might be more useful if qualifications were required before people were allowed to complain about open source software on internet message boards. That’ll be the day!

In terms of abuse, I was thinking of this issue thread: https://github.com/RsyncProject/rsync/issues/929

AFAIK the rsync maintainer does it for free. And he mainly seems to be getting abuse in return for that service.

It's also worth noting that the vulnerability you link to is a denial of service vulnerability. While yes, this is technically a vulnerability, it's not the sort of thing that people are usually worrying about in the context of null pointers. If features that give rise to DoS vulnerabilities are the ones to worry about, top of the list would have to be backtracking regex engines: https://owasp.org/www-community/attacks/Regular_expression_D...

Here’s a concrete example of conservative AI usage: I use Claude to vibe code my nvim config. Now, who cares if my nvim config is AI slop? What’s the worst that can happen? Nvim works for me now way better than it ever did when I was limited by the time I was willing to spend configuring it manually.

Could you be more specific here? The article doesn't even say which problem Airbus are considered to be criminally liable for.

This doesn't even work as a metaphor. I absolutely would not jump on the chance to ride on a literal rocket ship without asking a hell of a lot of questions first!

The real answer to what's going on is one that HN doesn't like to consider. It's simply that a lot of people in a lot of countries are worried about what children are able to access on the internet and want the government to help restrict it.

I don't support these sorts of restrictions. However, HN seems completely unable to have a sensible discussion about them because most posters are convinced that this is all part of some kind of sinister authoritarian scheme. In reality, it's just some bad legislation pushed by various people who largely have good motives, and who are concerned about something that is a real problem.

The bad legislation should be opposed. In order to do so effectively, we have to address the actual concerns driving it, rather than railing ineffectually against a largely imaginary authoritarian conspiracy.

(Edit: I don’t disagree with Mozilla’s position, but failure to declare an obvious conflict of interest undermines their credibility.)