I pretty much agree with this article - It seems like LLM companies are just riding the hype, and the idea that LLMs will lead onto General AI feels like quite a stretch. They’re simply too imprecise and unreliable for most technical tasks. There's just no way to clearly specify your requirements, so you can never guarantee you’ll get what you actually need. Plus, their behaviour is constantly changing which only makes them even more unreliable.
This is why our team developing The Ac28R have taken a completely new approach. It's a new kind of AI which can write complex accurate code, handling everything from databases to complex financial models. The AI is based on visual specifications which allow you to specify exactly what you want, The Ac28R’s analytical engine builds all the code you need - No guesswork involved.
I saw how you handled numerical structures and it looks pretty good - the way you combine them reminds me of R but obviously it’s a lot more flexible. I think I can see how you handle sets of data although the random variables are a little above my pay grade. Is this something that people can play with?
Thanks for taking a look. Yes, we treat numerical structures as standalone entities that can be combined and manipulated. With some slight variations we do something similar for databases, sets and random variables. Basically, all of the iterative loops are hidden from view.
Unfortunately there is no easy way for people to play with it directly - its UI uses special expandable panels that would be difficult to build into a web page
This is why our team developing The Ac28R have taken a completely new approach. It's a new kind of AI which can write complex accurate code, handling everything from databases to complex financial models. The AI is based on visual specifications which allow you to specify exactly what you want, The Ac28R’s analytical engine builds all the code you need - No guesswork involved.