Unverified50% confidenceFactExact time

牛津词典收录约17万英语词汇

1

Sources

50%

Confidence

Long-term

Relevance

7/7/2026

First Seen

Sources

Why Large Language Models Are Starting to 'Invent Words': The Nature of LLM Language Boundaries

hackernewshackernews7/6/2026

Related Claims

Unverified1 million tokens is equivalent to approximately 7.5 million English words.67% similar UnverifiedThe vocabulary of a standard autoregressive language model typically contains 32,000 to 128,000 tokens.67% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/168699

API

curl https://kongchang.com/api/v1/knowledge/claims/168699

MCP

get_claim(id=168699)