Thoughts on Evals
raindrop.ai
Thoughts on Evals
1–10 of 17 posts
Re: Thoughts on Evals
#2Both of these are kind of silly and vendors trying to sell you tooling you probably don't need.
In a gold rush, each is trying to sell you a different kind of shovel claiming theirs to be the best when you really should go find a geologist and and figure out where the vein is.
Re: Thoughts on Evals
#3The framing in this post is really weird. Automated evals can be much more informative than unit tests because the results can be much more fine grained. A/B testing in production is not suitable for determining whether all of one's internal experiments are successful or not.
I don't doubt that Raindrop's product is worthwhile to model vendors, but the post seems like its audience is C suite folks who have no clue how anything works. Do their most important customers even have any of these?
Re: Thoughts on Evals
#4Founder of a/b testing company accuses founder of evals company of misrepresenting how a/b tests are used in practice, then concludes by misrepresenting how evals are used in practice: "Or you can write 10,000,000 evals."
Could've easily been framed as "you need both evals and a/b testing," but instead they chose this route which comes across as defensive, disingenuous, and desperate.
BTW, if a competitor ever writes a whole post to refute something you barely alluded to without even mentioning their name... congratulations, you've won.
Re: Thoughts on Evals
#5This scared me until I realized it is about raindrop.ai, not raindrop.io.
(Raindrop.io is a bookmark service that AFAIK has "take money from people and stores their bookmarks" as its complete business model.)
Re: Thoughts on Evals
#6> Intentionally or not, the word "eval" has become increasingly vague. I've seen at least 6 distinct definitions of evals
This. I am so tired of people saying evals without defining what they mean. And now even management is asking me for evals and why we are not fine tuning.
Re: Thoughts on Evals
#7The framing in this post is really weird. Automated evals can be much more informative than unit tests because the results can be much more fine grained. A/B testing in production is not suitable for determining whether all of one's internal experiments are successful or not. I don't doubt that Raindrop's product is worthwhile to model vendors, but the post seems like its audience is C suite folks who have no clue ho…
I think in most cases, outside of pure AI providers or think AI wrappers, almost every team will realize more gains from focusing on their user domains and solving business problems versus fine tuning their prompts to eek out a 5% improvement here and there.
Re: Thoughts on Evals
#8The framing in this post is really weird. Automated evals can be much more informative than unit tests because the results can be much more fine grained. A/B testing in production is not suitable for determining whether all of one's internal experiments are successful or not. I don't doubt that Raindrop's product is worthwhile to model vendors, but the post seems like its audience is C suite folks who have no clue ho…
I think in most cases, outside of pure AI providers or think AI wrappers, almost every team will realize more gains from focusing on their user domains and solving business problems versus fine tuning their prompts to eek out a 5% improvement here and there.
I don’t think you can use this as a blanket statement. For many use cases the last 5-10% is the difference between demoware and production.
Re: Thoughts on Evals
#9Founder of a/b testing company accuses founder of evals company of misrepresenting how a/b tests are used in practice, then concludes by misrepresenting how evals are used in practice: "Or you can write 10,000,000 evals." Could've easily been framed as "you need both evals and a/b testing," but instead they chose this route which comes across as defensive, disingenuous, and desperate. BTW, if a competitor ever writes…
Agree. This whole post comes across as sales rather than the truth that both are useful for different things
Re: Thoughts on Evals
#10No, thanks. Just use evals with error bars. If you can't get error bars, use an A/B test to detect spuriousness and evals.