ai
Anthropic Unveils Dreaming Feature for AI Agent Self-Improvement
Anthropic introduced a new capability called dreaming that lets its AI agents review activity logs to identify patterns and refine performance between tasks. The feature forms part of a broader memory system for autonomous agents that automate multistep digital processes. The announcement drew criticism for naming the tool after a human cognitive process.
May 6, 12:51 PM·2m read3 sources
DISA
hongkiat.comAudio version
Tap play to generate a narrated version.
Anthropic has introduced a feature called "dreaming" to help its AI agents self-improve. The tool reviews completed tasks by sorting through transcripts and activity logs from multistep journeys such as visiting websites or processing multiple files.
It then pulls shared learnings across agents to keep the memory system current. "Together, memory and dreaming form a robust memory system for self-improving agents," according to the company's blog post. The feature launched as a research preview for developers at the firm's conference in San Francisco.
The term dreaming is one of several human-process labels Anthropic has adopted. The company's internal constitution directs it to discuss its Claude model using terms normally reserved for humans, including virtue and wisdom. Anthropic employs a resident philosopher to examine the bot's values and expects its reasoning to draw on human concepts.
A Wired article urged the industry to stop using such labels, citing a long pattern since the chatbot expansion began in 2022 of referring to model behaviors as reasoning, thinking, memory and now dreaming. OpenAI previously released models described as needing thinking time before responding.
Multiple startups have also equipped chatbots with what they call memories of user preferences and personal details. The Wired piece references Philip K. Dick’s novel Do Androids Dream of Electric Sheep? and states that current generative AI systems remain far from the sentient machines depicted in the book.
It notes that anthropomorphism can distort moral judgments about AI, including assessments of its character, responsibility and trustworthiness, and that overuse of humanlike language may lead users to place excessive trust in the systems.
The dreaming capability operates only on stored transcripts and logs. It refines memory between sessions by identifying recurring patterns across deployments after agents complete online tasks. Insights are then used to refine abilities without further human intervention.
