Sleep-time Compute | Letta
Sleep-time compute is a new way to scale AI capabilities: letting models "think" during downtime. Instead of sitting idle between tasks, AI agents can now use their "sleep" time to process information and form new connections by rewriting their memory state.
BRIEF Sleep-time compute is a new way to scale AI capabilities: letting models "think" during downtime. Instead of sitting idle between tasks, AI agents can now use their "sleep" time to process information and form new connections by rewriting their memory state. Read our research paper here , and learn how to make sleep-time agents in Letta on our docs . From test-time scaling to sleep-time scaling Over the past year we’ve witnessed the rise of the “reasoning models”: models that "think" before they answer. Recent models such as OpenAI's o1, DeepSeek's R1, and Anthropic's Claude 3.7 don’t re
saved by
related reading
- Introducing Context Repositories: Git-based Memory for Coding Agents | Lettaletta.com
- Continual Learning in Token Space | Lettaletta.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Do Language Models Need Sleep? Offline Recurrence for Improved Online Inferencearxiv.org
- Lettaletta.com
- LLM Daydreaming · Gwern.netgwern.net
- Measuring AI Ability to Complete Long Tasks - METRmetr.org
- Memory Models: Towards Agents That Learnletta.com
- GitHub - karpathy/autoresearch: AI agents running research on single-GPU nanochat training automaticallygithub.com
- Unlocking the Working Memory of Large Language Models for Latent Reasoningarxiv.org
- Noam Brown on X: "Implications of Large-Scale Test-Time Compute" / Xx.com
- Generative AI's Act o1: The Reasoning Era Begins | Sequoia Capitalsequoiacap.com