Announcement
Extropic uses reinforcement learning to post-train models for Thermo AI research
Extropic says the work aims to speed algorithmic discovery for what it calls a new species of computer.
TLDR
Extropic says it is using reinforcement learning to post-train models for Thermo AI research, aiming to accelerate algorithmic discovery for what it calls a “new species of computer.” It describes the work as the “first sparks of Thermo RSI,” in collaboration with Prime Intellect.
Combined views
279.4K
16 Sources, first seen ago
