Submitted by iamx9000again t3_11ybjsi in MachineLearning
I was watching the GTC keynote and became entirely overwhelmed by the amount of progress achieved from last year. I'm wondering how everyone else feels.
​
Firstly, the entire ChatGPT, GPT-3/GPT-4 chaos has been going on for a few weeks, with everyone scrambling left and right to integrate chatbots into their apps, products, websites. Twitter is flooded with new product ideas, how to speed up the process from idea to product, countless promp engineering blogs, tips, tricks, paid courses.
​
Not only was ChatGPT disruptive, but a few days later, Microsoft and Google also released their models and integrated them into their search engines. Microsoft also integrated its LLM into its Office suite. It all happenned overnight. I understand that they've started integrating them along the way, but still, it seems like it hapenned way too fast. This tweet encompases the past few weeks perfectly https://twitter.com/AlphaSignalAI/status/1638235815137386508 , on a random Tuesday countless products are released that seem revolutionary.
​
In addition to the language models, there are also the generative art models that have been slowly rising in mainstream recognition. Now Midjourney AI is known by a lot of people who are not even remotely connected to the AI space.
​
For the past few weeks, reading Twitter, I've felt completely overwhelmed, as if the entire AI space is moving beyond at lightning speed, whilst around me we're just slowly training models, adding some data, and not seeing much improvement, being stuck on coming up with "new ideas, that set us apart".
​
Watching the GTC keynote from NVIDIA I was again, completely overwhelmed by how much is being developed throughout all the different domains. The ASML EUV (microchip making system) was incredible, I have no idea how it does lithography and to me it still seems like magic. The Grace CPU with 2 dies (although I think Apple was the first to do it?) and 100 GB RAM, all in a small form factor. There were a lot more different hardware servers that I just blanked out at some point. The omniverse sim engine looks incredible, almost real life (I wonder how much of a domain shift there is between real and sim considering how real the sim looks). Beyond it being cool and usable to train on synthetic data, the car manufacturers use it to optimize their pipelines. This change in perspective, of using these tools for other goals than those they were designed for I find the most interesting.
​
The hardware part may be old news, as I don't really follow it, however the software part is just as incredible. NVIDIA AI foundations (language, image, biology models), just packaging everything together like a sandwich. Getty, Shutterstock and Adobe will use the generative models to create images. Again, already these huge juggernauts are already integrated.
​
I can't believe the point where we're at. We can use AI to write code, create art, create audiobooks using Britney Spear's voice, create an interactive chatbot to converse with books, create 3D real-time avatars, generate new proteins (?i'm lost on this one), create an anime and countless other scenarios. Sure, they're not perfect, but the fact that we can do all that in the first place is amazing.
​
As Huang said in his keynote, companies want to develop "disruptive products and business models". I feel like this is what I've seen lately. Everyone wants to be the one that does something first, just throwing anything and everything at the wall and seeing what sticks.
​
In conclusion, I'm feeling like the world is moving so fast around me whilst I'm standing still. I want to not read anything anymore and just wait until everything dies down abit, just so I can get my bearings. However, I think this is unfeasible. I fear we'll keep going in a frenzy until we just burn ourselves at some point.
​
How are you all fairing? How do you feel about this frenzy in the AI space? What are you the most excited about?