ai

Agile was a reaction to slow, expensive implementation. If AI collapses implementation cost to near zero, did we just accidentally resurrect the design-first methodologies it replaced?

Silicon Valley's founding thesis was that technology should empower humans to build new mediums. It forgot this. Now it sells shortcuts — and is building AI the same way, while the critics who should know better are arguing against the wrong thing.

Everyone talks about scaling technology. No one talks about scaling society. Is LLMs just bad or are there ways LLMs could be used to address deeply rooted societal issues?

Why coding agents will be the sticky application that remains after the current wave of AI hype passes

How formally verified and compiler-verified static type systems have become essential companions to AI-assisted coding, providing the safety rails that enable vibe-driven development at scale

Supervised goal conditioned reinforcement learning using generated intermediate goals.

Learning about how Contrastive Language-Image Pre-training (CLIP) works

ChatGPT poses threats to fundamental assumptions we make about the web and how we use it that exceed its threats to humanity in the near to medium term. The implications of blindly accepting this transistion could be far reaching and hard to return from

Writing a compiler for PyTorch that optimizes neural nets for NVIDIA GPUs

Showing how you can use DRIVE AGX and its suite of accelerators to achieve real-time perception for self driving cars

Making it super easy to get started with Deep Learning using Jupyter Notebooks and Docker

Making NVIDIA's Neural Network Optimizer accessible to the everyday data scientist