Simon Willison·· 18 d ago
Quoting Ted Sanders
Quoting Ted Sanders
AI summary
OpenAI's Ted Sanders explains that while LLM performance is multidimensional, much of the variation is explained by a single variable: model size. Bigger models are more performant and reliable, cost more per token, and have better recall of esoteric facts.
Selection record
Threshold 76Media and individualsFirst 22Second 22
Not admittedSum of both 44 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：讨论LLM性能与模型规模命名
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Simon Willison · simonwillison.net