Sublime
An inspiration engine for ideas
a quick note from @karpathy talk, which afterwards I was fully immersed in the talk I stopped writing down/taking notes:
While it is interesting to think about LLMs in terms of "electricity" -> CAPEX to train an LLM (~= to build the grid) -> OPEX to serve intelligence over increasingly homogeneous API (prompt, image,... See more
Nice article in Financial Time where I explain that Auto-Regressive LLM are insufficient to reach human-level intelligence (or even cat-level intelligence).
But alternative architectures that I call "objective driven" may reach human-level intelligence one day.
They use world models based on JEPA (Joint... See more
Yann LeCunx.com
Machine learning is not magic; it’s just multidimensional curve fitting.
Eric Redmond • Deep Tech: Demystifying the Breakthrough Technologies That Will Revolutionize Everything
This is, by the way, the dirty secret of the machine learning movement: almost everything produced by ML could have been produced, more cheaply, using a very dumb heuristic you coded up by hand, because mostly the ML is trained by feeding it examples of what humans did while following a very dumb heuristic. There's no magic here. If you use ML to... See more
Forget Privacy: You're Terrible at Targeting Anyway
Super interesting use case of Flux LoRA training. Using 3d sneaker models from blender for training set to train a LoRA (The sneaker model was trained using Fluxgym)
cocktail peanutx.com