The task described in this article is asking questions about a document that was provided to the llm in the context.

I would hope that if you give a human a text and ask them to cite facts from it they would do better than 99% correct.

Also, when the tokens exceeded 200k, the llm error rate was higher than 10%

To expand on that, even if you didn’t want to take the VC funded money and bootstrap your own business, the deck is stacked against you. If you compete in the same space, a VC funded company can do more marketing, develop the product faster, have more connections to important business partners because of large amount of money and connections they have.

And they will “outcompete” you at a loss, until the bootstrapped business goes under or settles for a tiny market share in a niche. So when they say, the economy is rigged, this is what they mean. You will need large amounts of capital to compete in the tech space. Even if you are two times smarter and work two times harder, you will never be able to compete with a VC funded company flushed with money in the same space unless you get reaaaally lucky.

Thanks! It took I don’t know how many tries to get a good one 😅

Thanks! Yes, its a very beautiful place. In summer we’re planning to visit again.

It‘s the original name of the place in Catalan

Black winged stilts

I don’t think so. These birds were quite small. Around 15 cm beak to tail.

Valid point about privacy issues. But actually this topic is also interesting in an industrial context when you want to know how much your machines are using to optimise your factory. But yeah, it always depends on how you use it.

I was investigating if these algorithms could be used in an embedded environment. Basically I implemented a load monitor on a raspberry pi using a pretty basic machine learning algorithm and checked performance. Performance wise it worked out pretty well but the accuracy was pretty bad on real world data. Like 50%. Of you’re interested in how it works I can give some more info.

Ooohh cool. Non-intrusive load monitoring. I did my bachelor’s thesis on that. Pretty interesting field