statement
'The end of diffusion' is hype; the better question is whether it is worth paying for more expensive training to get built-in verification and flexible compute at inference time — a real and interesting trade-off.
A statement by מייק. Statements are as reported by the cited publishers — not verified by DecisionGateway.
"סוף הדיפוזיה" זה הייפ. נכון יותר לשאול אם שווה לשלם על אימון יקר יותר כדי לקבל אימות מובנה וחישוב גמיש בזמן אינפרנס. זה טרייד-אוף אמיתי ומעניין.
Discussion
Related claims
Diffusion training is relatively simple regression — 'here is a noisy image (letter), guess the noise' — with no need for negative examples and no normalization constant to compute, which is why it is stable and scalable.post author · statementAlexi Gladstone's tweet is a good opportunity to clarify what an Energy-Based Model is, what a diffusion model is, and why the difference between them is smaller and more interesting than the hype suggests.post author · statementDiffusion is almost an EBM: the direction diffusion learns is exactly the gradient-descent direction of some energy (in the transition from noisy data to clean), meaning diffusion directly learns the slope of the energy surface and skips the energy itself — the very trick that bypassed the difficulty of training EBMs.post author · statementThe post's author concludes that in supervised learning a distribution shift between train and test is usually a problem, while for RL training it is part of the solution.כותב הפוסט · statementThis is a direct price/performance escalation in frontier AI.author · statementThe tool improved the speed of one of the foundational models on time series by about 3x as well (inference).post author · statement
More claims by מייק
In event-driven neuromorphic architectures, parts of the network that do not need to work simply stay at rest.statementIn event-driven neuromorphic architectures, memory is adjacent to the processor.statementIn event-driven neuromorphic architectures, time is a computational feature.statementThe future of AI lies not only in pushing more billions of parameters into hot GPUs, but in a smart combination of classic transformers and LLMs with event-driven neuromorphic architectures.predictionEBMs promised a revolution 20 years ago, and the problem was never elegance — it was training at scale.statement
All claims by מייק