Researchers let Claude Code discover AI scaling algorithms that humans probably wouldn't have designed
Quick Answer
Researchers from UMD, Google, and Meta utilized AutoTTS to enable a coding agent to autonomously discover AI scaling algorithms, achieving a 70% reduction in compute costs while maintaining accuracy.
Quick Take
Researchers from UMD, Google, and Meta utilized AutoTTS to enable a coding agent to autonomously discover AI scaling algorithms, achieving a 70% reduction in compute costs while maintaining accuracy. The search process cost only $40 and took 160 minutes, showcasing the potential for AI to innovate beyond human design capabilities.
Key Points
- AutoTTS enabled a coding agent to discover new AI control algorithms.
- The discovered algorithm reduced compute costs by 70% compared to traditional methods.
- The search process took 160 minutes and cost $40.
- This research highlights AI's potential to innovate beyond human capabilities.
- Collaborators included UMD, Google, and Meta.
Article Excerpt
From source RSS / original summaryResearchers 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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
