ETH Zurich and Prefrontal AI Unveil LSA Method Cutting Long-Context AI Compute by 72x

Researchers from ETH Zurich and Prefrontal AI introduced LSA, a hierarchical clustering technique that maintains attention accuracy at 10 million tokens while reducing compute by 72x.

Read the full story at AlphaSignal ↗

Timeline · 1 report

2026-11-03 00:04 · AlphaSignal
ETH Zurich's LSA Slashes 10-Million-Token AI Processing by 72x

More stories

OpenAI appoints former US Army Secretary Dan Driscoll to national security role — OpenAI News
Anthropic reports $17B quarterly revenue, mounting losses and spending commitments ahead of IPO — Reuters AI
Marvell to acquire Lumentum in $115 billion all-stock AI data-centre deal — DigiTimes Asia
OpenAI to merge ChatGPT's Chat and Work tabs into a single desktop experience — TechCrunch AI
Apple CEO John Ternus says company won't ship AI for AI's sake — Techmeme
Anthropic confirms new Claude Code limits to prevent recreating existing video games — Engadget
OpenAI launches Grid Protectors Program to cut data center power use during grid strain — OpenAI News
Israeli startup 42AI exits stealth with $62.5M seed for behavioral world model — TechCrunch AI

Get the daily brief of stories like this at 6:30 every morning →