Hacker News Reader

Aside. I find the "cost per task" charts both useful and uncanny. Is It better a model that takes me to 90% in 1 dollar or one that takes me to 95% in 2 dollars? Or a different model that too scores 90% in 1 dollar? How much will it cost me the last 10% or 5%? At the end of the day, cost to 100% is what matters and the half (90%) backed solution may require more to reach 100% (or not, who knows?)

View on HN

> Is It better a model that takes me to 90% in 1 dollar or one that takes me to 95% in 2 dollars?

It's pretty important to understand if your own work domain is one where the last 5% matters. In a lot of day-to-day software engineering tasks, it doesn't, and one can get crazy mileage out of the cheaper models. OTOH, if you are performing novel research, that last 5% may be worth whatever it costs...

The 90% and 95% are against some blend of tasks meant to be broadly representative. A pricey model seldom fails a problem that cheap models do well, so there's stratification of tasks by difficulty. Someone doing novel research may be in the "hard" 15% of the blend, where P(solution) goes from one third to two thirds.

On the other hand, if it's cheap to tell whether you got a good solution, and you think the 90 and 95% apply to your task blend, then it's almost always worth trying the cheap model first.

Reply on news.ycombinator.com