Gen-1: The Next Step Forward for Generative AI — Generating Videos

Because data sets are very heterogeneous, and a lot of work already goes into curating them to try and get the best model possible. Curation is limited though, because it reduces the data set size and the model is still equally weighting everything in the data set, just without the worst stuff.

By annotating the data set, you avoid reducing data set size while simultaneously teaching the model the difference between good and bad content.

Many models already use annotated data, but LLMs haven't leveraged it much thus far because they're still new-ish tech with architectures in flux, and they've been focused on improving general quality by scaling size/data. As LLMs become more commercially important and we run out of high quality training data, annotating existing data will become the cheapest route to improving output quality.

Here's what chatGPT has to say to you:

   ME: Someone on hackernews says you can't write code or craft essays or lie. Explain to him how he's wrong. 

   chatGPT: As an AI language model, I am capable of generating text that resembles code, essays, and lies. While I may not be able to execute the code I generate or experience emotions like lying, I can generate text that resembles these things based on patterns I have learned from the data I was trained on. The quality of my output depends on the context and prompt given to me, as well as my training data. However, I can certainly generate text that resembles code, essays, and lies.

   ME: He will then claim that the answer you just gave is so generic that it's proof you're just a big probability machine. Give a more nuanced answer to prove him wrong. 
   
   chatGPT: While it is true that I operate based on statistical probabilities and patterns learned from my training data, my responses are not purely random. I use a complex architecture that includes self-attention mechanisms, transformer layers, and dense neural networks to process the input and generate a response. This allows me to understand context, maintain coherence, and even generate novel text based on the patterns I have learned.

   chatGPT: Additionally, my training data was generated by humans and therefore reflects human knowledge and behavior to some extent. This means that I can generate text that reflects human-like writing styles, knowledge, and reasoning.

   chatGPT: So, while I may not be capable of independent thought or creativity like a human, I can generate highly nuanced and sophisticated responses that go beyond simple statistical outputs. My ability to generate text that resembles code, essays, and even lies is a testament to the complexity of the AI models created by OpenAI.

I work with people who directly train LLMs. I can assure you if you think these things are probability machines, you have not played with it thoroughly. Alexa or cortana or even GPT-3 are more like probability generators. ChatGPT is different.

From one angle yes it is a probability machine. But from that angle, EVEN your own human brain is a probability machine as well. They are both neural nets.

It understands you.

Read this to the end: https://www.engraved.blog/building-a-virtual-machine-inside/

All the tasks it did in that article. Not just what it did initially but all the way to the ending shows that chatGPT understands you. It IS an inflection point. You just missed it. You're probably dismissing it because you've been reading the same old hype over and over again without realizing something different came out with chatGPT.

"Understanding" is meaningless. All that matters is "does the model produce good output?" People are excited about AI now because we've crossed over boundary with generative models, allowing them to be used in much more interesting ways. Previous machine learning applications were mostly regression and classification problems in fancy clothing.

ChatGPT is the "Newcomen engine" moment for AI. We've still got the AI equivalent of railroads, cars and jets in our future. There's absolutely zero chance that as we evolve these models and link them together it isn't transformative in the way we do work and run society.

> AIs with an 's', it's not a single entity, it's multiple completely unrelated tools, of course if you put them under the same individual "AI" name it seems amazing

What a bizarre, nonsensical argument. By that logic, the current state of a technology could not legitimately be considered "amazing" if any subset of it is not "amazing". Utter nonsense.

Regardless, I didn't even claim it was "amazing". That's your introduction. What I claimed was that current AI technology passes tests that assess whether or not it is "intelligence". In AI, that's the de facto paradigm shift.