Tag
Nicholas Carlini demonstrates that a modern Stockfish port running on a 1996-era 200 MHz Pentium Pro achieves ~3300 Elo, far surpassing Kasparov's ~2800, showing that most of the +1335 Elo gain since 1996 comes from better programming (+720) rather than faster hardware — meaning Deep Blue's custom supercomputer was never necessary.
Microsoft announces MAI-Image-2.6, an image generation model that ranks No. 2 on the Arena text-to-image leaderboard, improving on its predecessor with gains in text rendering, photorealism, and other categories.
Proposes DD-Elo, a chess rating system that integrates move-level data via a drift-diffusion model to accelerate skill assessment and rating adaptation, while maintaining alignment with traditional Elo.
A revamped TTS benchmark introduces objective standards and live blind voting to create an ELO rating for 46+ models, with participation open to the community.