Ah, wouldn’t be an LLM discussion thread without one of these “it works/doesn’t”... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		yoyohello13 6 months ago \| parent \| context \| favorite \| on: AccountingBench: Evaluating LLMs on real long-hori... Ah, wouldn’t be an LLM discussion thread without one of these “it works/doesn’t” conversations.

mdaniel 6 months ago [–]

If it makes you feel any better, the other infamous one "I spend so much time chasing hallucinations, I could have done it myself" is currently a sibling comment

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact