> tl;dr: Children learn unsupervised and without back propagation. Well, this has been talked about for at least 10 years. Just take a look at any talk/FAQ by Hinton and/or LeCun from 2012 and onwards.
If anybody is wondering SOBBED (#50BBED[1]) is pretty close to Zima Blue[2]. [1]: https://color-hex.org/color/50bbed [2]: https://en.wikipedia.org/wiki/Zima_Blue_and_Other_Stories
I had the same issue. I generated random numbers and still got over 60 years old. I had to dive deep into it, and it turns out that the original paper is shit. They ask participants to make sequences that are as random…
It does feel like a GPT-3 bot. I tried testing the GPT3-Davinci model with similar prompts and I get 3 to 5 of the same 10 recommendations.
They literally hire the smartest people they can find for this, e.g. David Donoho [1] [1] https://en.wikipedia.org/wiki/David_Donoho
Thank you for sharing this. Here is an official (free) link with better resolution: https://www.nfb.ca/film/to_be/
> tl;dr: Children learn unsupervised and without back propagation. Well, this has been talked about for at least 10 years. Just take a look at any talk/FAQ by Hinton and/or LeCun from 2012 and onwards.
If anybody is wondering SOBBED (#50BBED[1]) is pretty close to Zima Blue[2]. [1]: https://color-hex.org/color/50bbed [2]: https://en.wikipedia.org/wiki/Zima_Blue_and_Other_Stories
I had the same issue. I generated random numbers and still got over 60 years old. I had to dive deep into it, and it turns out that the original paper is shit. They ask participants to make sequences that are as random…
It does feel like a GPT-3 bot. I tried testing the GPT3-Davinci model with similar prompts and I get 3 to 5 of the same 10 recommendations.
They literally hire the smartest people they can find for this, e.g. David Donoho [1] [1] https://en.wikipedia.org/wiki/David_Donoho
Thank you for sharing this. Here is an official (free) link with better resolution: https://www.nfb.ca/film/to_be/