longer outputs

1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Nov 1, 2024 by Shawn Wang · across every show →

Everything said about longer outputs, oldest first

Nov 1, 2024 neutral

Assertion Supported

Swyx: Humans demonstrably prefer longer outputs in LLM evaluation

“The classic one for human preference evaluation is humans demonstrably prefer longer contexts or longer outputs, which is actually something that we don't necessarily want.”

Shawn Wang Nov 1, 2024 ▶ 13:05 In the Arena: How LMSys changed LLM Benchmarking Forever

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

longer outputs

Everything said about longer outputs, oldest first

Turn any episode into a week of clips.