Indexed regex search for large codebases, powered by trigram / sparse n‑gram indexes. A grep-like CLI that builds a local on-disk index, so searches stay fast even on huge monorepos.
Doesn't seem to work on iPhone. I suggest having a button to toggle between mine marking mode and regular mode - I used that on my own little vibe-coded minesweeper clone here: https://tools.simonwillison.net/minesweeper
Oh, I see - double clicking only works when you have already marked the correct number of adjacent mines. I didn't remember that's how it worked in the original.
I also never knew it was called "chording", that's worth an explanation.
I argue that we’re thinking about the singularity wrong. Instead of one superintelligent AGI, we’re already seeing swarms of stochastic LLM agents coordinating online, cross‑validating each other, pursuing goals, and even resisting shutdown. This post makes the case that emergent, unpredictable swarm behavior is the real threshold and that we may have crossed it without noticing.
I wrote a concrete expected‑value model for AGI that anchors rewards in the 15–30T USD Western white‑collar payroll, adds spillovers on 60T GDP, includes transition costs, and varies probability explicitly. Three scenarios (optimistic, mid, pessimistic) show when the bet is rational versus value‑destroying—no mysticism, just plug‑and‑play numbers. If you’re debating AGI’s payoff, benchmark it against actual payroll and GDP, not vibes.
based on algorithm from cursor team: https://cursor.com/blog/fast-regex-search
reply