TypeSafe's Jev, a "System One Model" trained with RLCD, claims to be 20-200x faster and 40-400x cheaper than small frontier LLMs, offering parallel sampling, "no hallucination", and calibration, and is suited for structured classifiers/judges/routing policies in production systems. AI summary
Firehose
Filtered to People, tagged “frontier models” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives