I checked with the team and it may have been some temporary rate-limiting issue.... | Hacker News

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

		cgorlla 3 days ago \| parent \| context \| favorite \| on: Launch HN: Mentat (YC F24) – Controlling LLMs with... I checked with the team and it may have been some temporary rate-limiting issue. We've rectified the results, it seems to be an isolated case. https://www.ctgt.ai/benchmarks

rancar2 3 days ago | [–]

Thanks for the thoroughness! I look forward to the next steps as you all apply this approach in other unique ways to have even better results.

SomaticPirate 3 days ago | [–]

Are these benchmarks correct that adding Anthropic's Constitutional AI system prompt lowered results across all the models?

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