Show HN: LOL Bench – a benchmark for whether LLMs get jokes l lolbench.lol 1 yakshithk_ 1 month ago 2 comments
Ask HN: How do you catch regressions when you change your AI agent's prompt? 1 yakshithk_ 5 months ago 2 comments
Ask HN: Why is cursor / Claude Code is so bad at generating readmes? 4 yakshithk_ 9 months ago 3 comments
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!