← All topics

llm prompting

2 captures, most recent first.

Captain Pleasure, André... @Algomancer

— saved image

Captain Pleasure, André... [verified] @alg... · 14h
Yes, sure, AI improves mathematical performance when you tell them to 'believe in yourself'. But this hasn't been tried in humans yet – has anyone with pom poms gone to a math department and, approaching the nerdiest dork, constantly showered him/her with wholesome encouraging words while working on an open problem? For hours? The most encouragement mathematicians get is usually in short bursts, often way past their prime. I bet it would help a mathematician in peak performance more than even methylphenidate!
Note from Claude Sonnet 5

Tweet joking that if telling AI models to 'believe in yourself' improves their mathematical performance, the same untested intervention (constant cheerleader-style encouragement) might help human mathematicians more than stimulant medication like methylphenidate.

llm promptingmathematicshumortwitter

vie @viemccoy

— reposted by j⧉nus

↻ j⧉nus reposted vie ◇ (@viemccoy ✓) — 3h You can retain your normative and well-grounded scientific epistemology and still admit that prompting language models is obviously a form of casting spells.
Note from Claude Sonnet 5

Text-only tweet, no images; engagement counts cut off at bottom of crop.

llm promptingai culturetwitterepistemics