As many standardized-test-takers know, there are two ways to score highly on a test: learn the material, or guess what the question-writer is thinking. LLMs have gotten really good at the second part!
I'm not saying it wasn't a good joke, but maybe don't open with it.
☀️ Starshine
Stephen Judkins
His Wikipedia page suggests he was pretty open minded.
Hyundai is teasing their New York Auto Show unveiling with this photo of a large, floating rock and they're saying it will be a "major world debut". Hmm...what vehicle do you think it could be?
Grace
USER WAS BLOCKED FOR THIS POST
now speculating what the "oomfies just broke up" bot would look like (someone unfollows their friend)
my prediction is em dashes and contrastive reframes
god I love geology FIGHT ME
fuck
Sam Ottewill-Soulsby
Thinking now about all the people on here who think that people who piss them off should be "wedgied" or "stuffed into lockers", and that assholes were clearly "not bullied enough as kids".
Your average person is PRO-bullying because they think bullying is how you encourage prosocial behaviour.
MotorWeek
There’s some cool recent research on this phenomenon! It turns out vision language models excel at image benchmarks *even when the actual images aren’t provided,* because the answers are implicit in the questions!
arxiv.org/abs/2603.21687
Multimodal AI systems have achieved remarkable performance across a broad range of real-world tasks, yet the mechanisms underlying visual-language reasoning remain surprisingly poorly understood. We r...
the followed bot being almost entirely sex and the blocked bot being almost entirely politics is so fucking funny
It's really instructive to look at an LLM's output and piece by piece look to see how much of it was already implicit in the prompt, and where exactly. It makes me realize how much I'm telling on myself all the time.
