Strategy
SpikingBrain bets on sparse firing over brute-force compute
Most large models keep every parameter lit for every token, like a city that never turns the lights off. SpikingBrain borrows the brain's trick - fire only the neurons that matter - and reports order-of-magnitude efficiency on Chinese MetaX chips. The headline numbers are real, with conditions worth reading.
Lead essay
Start here when you want the current Doric argument instead of a chronological archive.
Read the note