@ylecun I like how “There” remains unaddressed.

@pentagoniac It was addressed and then de-addressed by recycling an older set of slides.

@ylecun Humans and animals are not built from scratch; both are born with varying degrees of instincts and mechanisms. Neural nets aim to be similar to a brain but without any of the foundational aspects.

@ylecun On that last point: humans seems to have an *open-ended creativity* too, in addition to objective-driven behavior. Not captured by the slide?

@ylecun Sometimes I hate you sometimes I love you

@ylecun My cat learns to do only nasty things, nothing useful at all! I doubt he's better at learning than RL model of his size

@ylecun It says that he doesn't know the difference in usage of "there" and "their."

@ylecun Very interesting. Tho for humans we have 247 stimulus and a lot more sensors / information input for learning. Anda lot of experience takes years to build up. Wonder if in future possible to emulate animal experience on a computer with enough compute.

@ylecun Interested to have your 2 cents on @hume_ai ?

@ylecun Is “common sense” the result of billions of years of evolution, encoded in our DNA (ultra-base model)?

@ylecun Sorry prof LeCun, but there is a misspelling on your slide for the word 'Their'! I used my uncommon sense for spotting that!😉

@ylecun huge 🫡

@ylecun Recent advancements in ML and AI allow us to solve a large number of problems we couldn't solve before. However we need to be realistic of what is really possible and what is not and acknowledge that we still have a long way to go to achieve real intelligence.

@ylecun If you want to speed up learning you need pain/pleasure valuing. Pain and pleasure are simply approach and avoid characterizing inclinations. Pain is an avoid reaction. It has features that include information why a pattern in data is undesirable. Pleasure is the opposite.

@ylecun It comes down to how one should learn the proper discretization of continuous state - action spaces.

@ylecun The typos are there to reassure the audience that you are human 🙂

@ylecun Humans and animals' intelligence is a byproduct of their intrinsic symbiosis of all signal emitors and sensors. Today's AI is nowhere near any of that.

@ylecun 😂We are carbon based intelligence, not silicon

@ylecun i will still be called "machine learning" ? all this terms should be rebranded ML : trained algorithm (TA) AI: just call it algorithm AGI: ungovernable by human algorithm, but observable ASI: ungovernable and unobservable algo

@ylecun Ok…