AI Breakthrough: AutoTTS Algorithm Outperforms Humans, Slashes Compute Costs by 70%
A new AI-powered algorithm, AutoTTS, has been developed that can outperform human-designed algorithms in terms of accuracy and compute efficiency, achieving a 70% reduction in token usage. This breakthrough has significant implications for the development of large language models and their applications in various industries.
Researchers from UMD, Google, Meta, and other institutions use AutoTTS to let a coding agent independently discover control algorithms for AI reasoning. The algorithm it found cuts compute by about 70 percent compared to standard self-consistency while matching its accuracy. The whole search cost $40 and took 160 minutes. The article Researchers let Claude Code discover AI scaling algorithms that humans probably wouldn't have designed appeared first on The Decoder.