https://maggiemchen.com/ New writing from Maggie Chen. en-us https://maggiemchen.com/curious/vercel-ship-2026.html https://maggiemchen.com/curious/vercel-ship-2026.html What it takes to make agents useful once generating code is the easy part. Eleven takeaways from Vercel Ship: durable execution, portable context, generative UI, and verification engineering—with diagrams and frames from the livestream. https://maggiemchen.com/curious/generative-ui.html https://maggiemchen.com/curious/generative-ui.html Software stops being built and starts being summoned. The paradigm shift, the protocols (AG-UI, A2UI), the three structural patterns, PAGEN benchmark, vibe coding's QA crisis, and the bottlenecks that decide whether the whole thing scales. https://maggiemchen.com/curious/inside-the-model.html https://maggiemchen.com/curious/inside-the-model.html How frontier AI is being made transparent (mechanistic interpretability) and adaptive (continuous learning). Superposition, sparse autoencoders, the pragmatic pivot, catastrophic forgetting, and what changes for working data scientists. https://maggiemchen.com/curious/training-data.html https://maggiemchen.com/curious/training-data.html 24 months of frontier-model evolution as a field guide. Knowledge cutoffs, MoE routing, the synthetic-data loop, the transparency collapse. https://maggiemchen.com/curious/the-technology-trap.html https://maggiemchen.com/curious/the-technology-trap.html Carl Benedikt Frey's history of automation, translated for AI-era founders. Labor-enabling vs replacing, Engels' Pause repeating now, why the cluster traps itself, and TAM ≠ buyer. https://maggiemchen.com/curious/product-hunt.html https://maggiemchen.com/curious/product-hunt.html Six months of featured launches (3,311 of them), regressed with confidence intervals. https://maggiemchen.com/curious/llm-end-to-end.html https://maggiemchen.com/curious/llm-end-to-end.html Karpathy's 3.5-hour deep dive: tokenization quirks, SFT, RLHF, RL on reasoning, plus six pieces of "LLM psychology." https://maggiemchen.com/curious/llm-first-principles.html https://maggiemchen.com/curious/llm-first-principles.html His 1-hour intro distilled: two files, the zip of the internet, the reversal curse, the LLM OS analogy.