We need benchmarks that can distinguish between continuous learning and long-con... | Hacker News

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

jballanc 3 months ago | parent | context | favorite | on: We're running out of benchmarks to upper bound AI ...

We need benchmarks that can distinguish between continuous learning and long-context extrapolation.

vrighter 3 months ago [–]

oh that's easy: continuous learning is not something current architectures can do. So the benchmark for that can be done mentally

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