davinci

@leothecurious (davinci) — 12h u should actually feel lucky china isn't winning the frontier AI race, else we all would've had to put up with routine authoritarian practices such as topic-based output censorship, government-enforced access restrictions, and intelligence centralization in the hands of a few.

davinci @leothecurious · Oct 25 predictive coding doesn't merely serve to update parameters via local credit assignment but doubles as am algorithm for inference-to-best-explanation based on observed features (bottom-up signal) and learned priors (top-down signal). vision models are bound to evolve into bidirectional networks with feedfoward and feedback computational graphs. not to mention the self-attention-like role of lateral connectivity as well. the implications will be manifold. > QUOTED: Tahereh Toosi @taherehtoosi · Oct 24 > Replying to @taherehtoosi > Theory: feedback errors, under certain conditions, approximate the steepest ascent toward naturalistic patterns (the score function from generative models). These errors act like a... > [Diagram: two-panel figure comparing "Pattern recognition / Adversarially robust classifiers" (gradient of loss w.r.t. input, ∇L_x(x,y)) against "Pattern generation / Score-based generative models" (gradient of log-density, ∇log p_θ(x)), plus a 3D loss-landscape surface with a red dashed arrow labeled ∇log p(x) climbing toward a peak]