I’m surprised how many people seem offended by this comic. I found it pretty relatable. That doesn’t mean I “don’t understand context”, or think the writers were bad people, or that the shows aren’t worth watching. It just means I find it personally unpleasant to find these jokes in a work I’m otherwise enjoying.

When kids study older literature and media in school, generally when there’s a slur or racist reference or joke, the teacher will stop and explain the context and get the kids to reflect on it and why it’s probably not acceptable today. Even though I understand this and know it going in, I’m still kind of doing an abridged version of that in my head when something like this comes up in a show – I’ve been following along, laughing with the writers, and then suddenly I’m backing up and distancing myself from one joke or idea. It’s jarring, it pulls me out of the show, and it’s just not fun.

In some cases it also comes across as incredibly lazy and unoriginal. So many sitcoms from that era have “the trans episode”, “the gay episode”, “the lecherous character” – and they all make the same unfunny jokes, and it’s a reminder than a lot of these shows, even in their time, were just not that creative. Plenty of modern shows have the same problem, but they don’t draw attention to it by having large classes of “stock jokes” that simply do not land today.

Yeah, even though I have a bit of background I can’t really make heads or tails of that OpenSearch doc at a glance, it’s dense stuff.

In my experience knowing the keywords to stick in a search engine is often half the battle; there are plenty of resources out there on “vector databases”. “Semantic search” from the lede of the OpenSearch doc might be another good one to have around.

Feel free to ask me any other questions and I can try to answer to the best of my abilities, though again, not an expert and honestly I’ve never actually used these myself beyond toy examples.

I’m not an expert, but it sounds like you want an embedding+vector database. This essentially extracts the part of an LLM that “understands” (loaded term, note the quotes) the text you put in, and then does a lookup directly on that “understanding”, so it’s very good at finding alternate phrasings or slightly differing questions.

There’s no actual text generation involved, and no need to retrain anything when adding new questions.

OpenSearch has an implementation (which I learned about just now while writing this comment and thus cannot vouch for); you could start there.

My assumption for the key icon was something to do with PINs/passkeys, which kind of reinforces OP’s point.

Ngl I really want to know what the tick icon actually does now.

And “a11y” is the most obscure – dare I say… inaccessible – fucking abbreviation of “accessibility”. For years I only saw them in passing and assumed both these things were like, quirkily-named Javascript frameworks or niche standards documents or something, despite knowing quite well the concepts they actually refer to.