Content tagged with "AI" (11)

If you feed the LLM your project's architecture and conventions before asking it to write code, the output gets dramatically better, and here's what to include and what to skip.

AI coding assistants are basically a REPL that calls an LLM in a loop, and once you see the 200 lines that make it work, the magic disappears.

Karpathy's dense, opinionated survey of everything that changed in language models over 2025, written by someone who has built these systems himself.

The CLAUDE.md is the highest-leverage file in an agent-assisted repo. Writing a good one is mostly subtraction: keep the few instructions that change behavior, cut the rest.

LLMs made writing code faster but the hard part was never typing, it was understanding the problem, and that part hasn't gotten any easier.

Model ability is jagged rather than a single line you cross; the system that aces a hard task can fail a trivial one, which makes 'is it AGI yet' the wrong question.

Karpathy builds an autograd engine from nothing, one line at a time, until backprop is something you could re-derive yourself instead of a formula you take on faith.

Anthropic's interpretability team looks inside the model and catches it planning several words ahead and reasoning in a concept space shared across languages.

antirez argues reasoning models are nothing exotic, just the same next-token predictors trained to spend more tokens thinking before they commit to an answer.

O'Reilly takes the long view, noting that every generation declared programming dead when the abstraction had only risen a level, and AI is the next rise.

A level-headed field guide to treating AI as a coworker instead of an oracle. The framing is sound; little of it feels new once you already spend your days in these tools.