Firehose

Filtered to Hacker News, tagged “natural language processing” · clear filters

All PeopleCompaniesPapersPodcastsHacker News

Browse by tag

14 NOV 2026 · Hacker News · 90 pts · 53 comments
10 NOV 2026 · Hacker News · 34 pts · 31 comments ↗

Researchers at NeuraCryption have developed SPECTRA, a neural model compression framework that can compress LLMs by 2.80x to 3.31x in under 50 MB RAM, achieving near-lossless compression and real-time generation speeds. The framework is based on Shannon source coding theory and continuous rate-distortion bounds, and eliminates empirical calibration passes by analytically determining parameter sensitivity from learned normalization scales. AI summary