underscored — Underscored

@underscored

4 clips · 1 follower

Tag:benchmarkingClear

oneusefulthing.org

An opinionated guide to which AI to use to do stuff

One sign of how far AIs have come is that every one of the AI's notes was accurate and there were no hallucinated page numbers
— Ethan Mollick

4w ago

The record of a money manager who merely stays close to the market is not an outperformance record—it is a perfect recipe for underperformance after fees. The question is never 'did I beat the benchmark?' but 'did I add enough value to justify the cost of active management?' Most cannot answer yes, and most won't admit it.

1mo ago

upstartsmedia.com

This Startup Says It's Beating Anthropic And OpenAI In Industrial AI

If 78% sounds like a lackluster C+ grade to you, Bhushan explains that a single person, even an expert one, would likely fail the same test, scoring maybe 10% at best. "These are questions that would be complex for a human to even attempt," he tells Upstarts.

3mo ago

oneusefulthing.org

Sign of the future: GPT-5.5

It is increasingly hard to quickly demonstrate each generational change as AI has gotten better, since a lot of the old things AI was bad at, like math or counting letters in words, are now trivial for AI to do.

4mo ago

Underscored — save the words that stop you in your tracks.

Start saving quotes →