Alec Radford tests Hassabis’s AGI challenge with a model trained on pre-1931 data
哈萨比斯出的难题,GPT之父接上了:用一个知识停在1930年的模型
Alec Radford’s team trained 13B talkie on 260B English tokens dated before 1931. They tested surprise on nearly 5,000 historical events and used HumanEval for lower-contamination code evaluation. The key issue is time leakage: the 13B model still has vague post-WWII knowledge.
Why it matters: Alec Radford's team trained a 13B model on pre-1931 English text and tested its surprise at post-war events across nearly 5,000 historical events, a reference point for data contamination and eval design.