What happens when an LLM never sees material beyond fifth grade?

·Hacker News··

LittleLearner Chat Findings Models Sandbox Cite LittleLearner Language Models Under Pedagogically-Controlled Knowledge Exposure A language model that only knows what a 5th grader knows. Fanfei Li1,2*† · Jana Zeller1,2,3* · Manuel Prada-Corral1,2,3 · Thaddäus Wiedemer1,2 · Prasanna Mayilvahanan1,2 · Ryan Cotterell3 · Wieland Brendel1,2 1MPI for Intelligent Systems  ·  2ELLIS Institute Tübingen  ·  3ETH Zürich *Equal contribution  ·  †Correspondence to fanfei.li@tuebi

Read full article →

Related Articles

Private German rocket makes history, reaches orbit from European soil
bookmtn · Hacker News · 3h ago
LLMs as a Cognitive Virus
canjobear · Hacker News · 3h ago
Actively exploited sandbox RCE in all Chromium versions
negura · Hacker News · 1d ago
Formalizing Fermat's Last Theorem
jlebar · Hacker News · 1d ago
Why are European countries moving their gold out of North America?
ranit · Hacker News · 18h ago