[segh]

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.

[cube00]

> because in 6 months when the AI labs release a more capable model

How many years do we have to keep hearing this line? ChatGPT is two years old and still can't be relied on.

[postexitus]

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.

[alltoowell]

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.

[segh]

For me, they have come from the AI labs themselves. I have been impressed with Claude Code and OpenAI's Deep Research.

[techpineapple]

In 6 months when FSD is completed, and we get robots in every home? I suspect we keep adding features, because reliability is hard. I do not know what heuristic you would be looking to conclude that this problem will eventually be solved by current AI paradigms.

[thornewolf]

GP comment is what has already happened "every 6 months" multiple times