WORTH TESTING · 25 OCTOBER 2026
Lee Robinson's Stanford lecture: how always-on AI agents work
Verdict: the clearest explanation we've seen of 'agents that work while you sleep'; advanced and coding needed if you want to build one, but the ideas help anyone choosing an agent product.
Sources
Worth testing
Lee Robinson's Stanford lecture: how always-on AI agents work: steps to try, cost and caveat
How we knowCompany figures are labelled as their own claims; anything we couldn't verify is labelled as a report or a claim.
MORE FROM 25 OCTOBER 2026
- Kimi K3.1 Pro: a leaked brief alleges a paid, unlabelled influencer campaign
- OpenAI is using discounts to win Anthropic's coding customers
- How Anthropic keeps Claude Duet away from your passwords and money
- OpenAI's Codex CLI 0.164 adds reusable prompt presets
- Rumours from the leak trackers: Gemini 4 'Carbon', a new Google image model and Qwen 4
- Report: Perplexity's 'Taste' skill is free until 31 October