←back to thread

419 points serjester | 1 comments | | HN request time: 0.238s | source
Show context
segh ◴[] No.43536147[source]
Lots of people are building on the edge of current AI capabilities, where things don't quite work, because in 6 months when the AI labs release a more capable model, you will just be able to plug it in and have it work consistently.
replies(3): >>43536288 #>>43536450 #>>43537390 #
postexitus ◴[] No.43536450[source]
and where is that product that was developed on the edge of current AI capabilities and now with latest AI model plugged in it's suddenly working consistently? All I am seeing is models getting better and better in generating videos of spaghetti eating movie stars.
replies(2): >>43536903 #>>43541070 #
1. alltoowell ◴[] No.43541070[source]
They're coming. I've seen the observability tools try to do this but I still have to tweak it. it's just time-consuming. Empromptu.ai is the closest to solving this problem. They are the only ones that have a library that you install in your to do system optimization, evals, for accuracy in real-time.