Machine learning as a form of data compression by 
Ciro Santilli 35 Updated 2025-01-10 +Created 1970-01-01
Ciro Santilli 35 Updated 2025-01-10 +Created 1970-01-01Philosophically, machine learning can be seen as a form of lossy compression.
And if we make it too lossless, then we are basically overfitting.
Our Final Invention - Artificial General Intelligence by Sciencephile the AI (2023)
Source. AGI via simulation section.Ciro Santilli defines an "AI game" as:
a game that is used to train AI, in particular one that was designed with this use case in mind, and usually with the intent of achieving AGI, i.e. the game has to somehow represent a digital world with enough analogy to the real world so that the AGI algorithms developed there could also work on the real world
Most games played by AI historically so far as of 2020 have been AI for games designed for humans: Human game used for AI training.
Ciro Santilli took a stab at an AI game: Ciro's 2D reinforcement learning games, but he didn't sink too much/enough into that project.
A closely related and often overlapping category of simulations are artificial life simulations.
Bibliography:
PCIe computer explained by ExplainingComputers (2018)
Source. Pre-trained computer vision model CLI by Ciro Santilli 35 Updated 2025-01-10 +Created 1970-01-01
Ciro Santilli 35 Updated 2025-01-10 +Created 1970-01-01Creator of Primer
youtube.fandom.com/wiki/Primer gives real identity:Feels exactly the background you'd expect: disilusioned by the educational system, and working to make education better! Great guy! Reminds Ciro Santilli of himself a bit.
- the name is Justin Helps from Minnesota
- dropped out of his PhD that got boring, and used to work at Khan Academy
- LinkedIn gives PhD subject: www.linkedin.com/in/justin-helps/ as materials science
- twitter.com/helpsypoo personal Twitter account
Face reveal at: www.youtube.com/watch?v=QC91Bf8hQVo
There are unlisted articles, also show them or only show them.