esc27

30% might be high. I've worked with two different agent creation platforms. Both require a huge amount of manual correction to work anywhere near accurately. I'm really not sure what the LLM actually provides other than some natural language processing.

Before human correction, the agents i've tested were right 20% of the time, wrong 30%, and failed entirely 50%. To fix them, a human has to sit behind the curtain and manually review conversations and program custom interactions for every failure.

In theory, once it is fully setup and all the edge cases fixed, it will provide 24/7 support in a convenient chat format. But that takes a lot more man hours than the hype suggests...

Weirdly, chatgpt does a better job than a purpose built, purchased agent.

Livesavers candy got me through several physics lectures in college.

Lately I've started taking dove dark chocolates on longer road trips.

TotK felt more empty to me, but that's probably a combination of already knowing the map and lacking Kass.

Yeah, I don't see AI as invaluable, at least not as it is now, but microwaves? I personally would not want a kitchen without one.

So a tool that is largely useless for people with training, experience, and time. But invaluable for others who figured out how to incorporate it into their work flows as well as those who have no time and simply need to eat something.