Model can accept 1M tokens doesn't mean it can reason across those 1M tokens

A Prime Intellect engineer revealed that GPT-5.5's retrieval accuracy drops from 80% at 256k tokens to 36% at 1 million tokens, a phenomenon called 'context rot,' and argued that bigger context windows are not a solution for AI agents. Andrew Ng released a free course on Claude Code, covering its agentic architecture and codebase interaction, in collaboration with Anthropic.

Prime Intellect engineer: "everyone's bragging about a million-token context. here's what they don't tell you. at 256k tokens GPT-5.5 scores 80% on retrieval. push it to a million and it drops to 36%. the model accepts the context, it just can't reason across it. people call it context rot." in a 20-minute talk he explains why bigger context windows won't save your agents. continual learning + training on your own traces + real environments - that's the fix. Watch the talk, then save Andrew Ng just dropped a free course on Claude Code from scratch, taught with the Anthropic team: 00:00 - why Claude Code is so agentic 04:00 - shockingly simple architecture 12:00 - point it at any codebase this short watch will replace 10 paid coding agent courses. Andrew Ng