yakshithk_
Re:Show HN: LOL Bench – a benchmark for whether LLMs get jokes
on Thursday September 10, 2026 @03:47PM (#49649275)
hey, builder here. The short version:
LLMs take three tests:
explain why jokes work (or don't), write jokes under shared premises or predict which jokes humans prefer
The finding so far that surprised me: every model aces explaining real jokes (95%+) but drops hard on explaining why a failed joke fails (81–92%).
happy to answer anything about the eval system and open to any sort of feedback!
Ask HN: How do you catch regressions when you change your AI agent's prompt?
i've been building agents for a while and kept running into the same problem: change the sys prompt, swap models, or tweak for the agent calls a tool — and something subtly breaks. The only way I found out was manually running it or a user reporting it.
Theres no mainstream AI video editing tool?
ik theres a few yc companies doing this but are they any good before I try them out?
Theres no mainstream AI coding tool?
ik theres a few yc companies doing this but are they any good before I try them out?
Why is cursor / Claude Code is so bad at generating readmes?
Is there any "cursor for excel / sheets"
have some mundane stuff to do and just wondering if there's an easier way to do this lol