_tpdt

“Lenat argues that we just don't have the data needed to reach common sense through these newer methods. Common sense isn't written down. It's not on the Internet. It's in our heads. And that’s why he continues to work on Cyc.”

“At one point, Lenat remembers, it suggested he could win the game by changing the rules. But each morning, Lenat would rejigger the system, pushing Eurisko away from the ridiculous and toward the practical. In other words, he would lend the machine a little common sense.”

Really enjoyed this 2016 article.

For safety-critical applications that use black-box ML models, I feel like a rules-engine paired with a knowledge graph needs to kinda sandwich the ML black box —- to “prompt engineer” the input and ensure the output aligns with common sense and safety standards.

Edit: clarity

You can connect tableau public to google sheets

I made this explainer for people with a light math background to understand the basic mechanics of neural networks -- some key concepts are left unexplained (e.g. backprogropagation) in order to focus more on how the models function. Would appreciate any feedback

huh thats really interesting and good to know -- thanks!

my thinking on not doing the IR blaster remote or dealing with the TV receiver, is the mechanical hand approach could work on non-television options (like a projector where your chromecasting a tv stream)

that looks super cool - appreciate the suggestion!

thats a solid suggestion, especially for a proof of concept

If anyone thinks this is seriously a good idea, I'd be very interested in collaborating. If someone wants to use the idea and not reach out to me, I would be happy to be your customer.