I’m glad you’ve gotten some actual use out of the LLMs! My outlook is more skeptical because I’ve seen too many interns get stuck on projects because they tried to ask LLMs for advice (which they did not double check) instead of reaching out to an experienced dev. The word calculators can only do so much.

In case my edit didn’t land in time: what makes the AI approach better than using existing non-AI static analysis tools

Become “pretty close to an expert” by… outsourcing the process of improving your code to a machine…

Even if it improves your code in that scenario, you’re not going to really understand what it’s doing or why. You can use AI as a shortcut for scripting, but you can’t use it as a shortcut for learning

Edit: Besides, we already have perfectly good static analysis tools. Just use a linter. Trying to use AI as a linter will just be worse and unpredictable compared to using an actual linter

immortality

so you can pet cats

If anyone wants proof, I’m perfectly willing to DM some Blue Origin stuff that shouldn’t be public

I don’t suggest doing this. It’s not like we’d even be able to confirm whether it’s legit or not.

The test was never meant to be a metric for whether something is good or not. It’s meant to be a metric for representation of women in media.

The test is based on this 1985 comic from Alison Bechdel’s “Dykes to Watch Out For”:

With that history in mind, I don’t think the fact that lesbian porn passes is a shortfall of the test. The test was created by lesbians, after all.