#ai-agents

Andrej Karpathy on why OpenAI’s first computer-use agents failed, why model capability had to come first, and why agent builders should think in decades rather than demos.

Notes from Thariq's X Article on Claude Fable, unknown unknowns, blind-spot passes, prototypes, interviews, references, implementation notes, and why agentic coding is increasingly about discovering what the human has not specified yet.

Notes from Lenny's Podcast with Andrew Ambrosino on Codex, cheap implementation, taste, role collapse, dogfooding, product planning, and why the future of work may look less like chat and more like a home base for delegated action.