AI Research

Anthropic says agents should dream offline

Anthropic says offline dreaming lifted Claude from 13% to 48%, and small, tested memories beat large logs.

StartupHub.ai Staff

By StartupHub.ai Staff, reviewed by Daniel Singer, Editor

3 min read

Claude agent memory diagram with notes and dreaming passes
Credit: Anthropic Engineering

Anthropic Engineering says offline dreaming lifted Claude from 13% to 48% on 25 questions.

Agents now work across sessions. Logs pile up fast. Memory must persist without polluting context. Anthropic defines memory as experience kept between sessions and reread as context, per its post. That definition excludes weight changes, in-session learning and compaction.

Memory is a prediction. A saved rule bets a future session will need it. That bet paid off on Continual Learning Bench 1.0, per Anthropic. Claude started each database question fresh but could read a persistent memory folder.

Newer models closed the learning loop. Claude Sonnet 4.6 left untested guesses scattered across files, per Anthropic. Claude Opus 4.7 consolidated notes and marked checked facts. Claude Opus 5 wrote rules, cited how each rule was verified and flagged traps. Claude Opus 5.5 and Sonnet 5.5 also closed the loop, with slightly higher baselines without memory.

The Pokémon Red test was starker. Claude Sonnet 3.7 wrote 413 files in 225 folders and won one badge, per Anthropic. Claude Fable 5 wrote nine files in two folders plus global.md and won four badges. Sonnet 3.7 logged battles and map positions that went stale. Fable 5 kept goals, gym plans and tested rules. After seven failed balls on a Magikarp, it saved a timing trick. Opus 5.5 kept a similarly small folder and finished the game.

Strict instructions hurt stronger models. Telling Opus 5 and Opus 4.7 to record only failures cut much of the memory gain, per Anthropic. Older models needed steering. Prompting Sonnet 4.6 to read memory and test theories nearly doubled its CL-Bench score. Sonnet 5 already read memory in 9 of 10 sessions without prompting, compared with less than half for Sonnet 4.6.

Dreaming fixed errors that raw notes preserved. Near Mt. Moon, Claude mislabeled a PokéCenter and declared the cave done, per Anthropic. It then hit a one-way ledge three times and retreated to Pewter City. Replaying the transcript against the note corrected the location. With the fix, Claude re-entered the cave and reached Cerulean City. No memory and raw memory both failed the route.

The same offline pass built navigation. Over 128 dreaming sessions, Opus 5 agents explored about 350,000 Stainless files totaling roughly 420M tokens and built a linked wiki, per Anthropic. Practitioners already distilled that workflow, with a DEV Community explainer framing it as notes, salience judgments and dreaming. The cost is real: gains required repeated passes, and stale notes still mislead until checked.

Mentioned in this story

Sources

Get the free daily brief every morning

Every morning the day's AI news, new AI startups and new funding rounds. Free and takes a few minutes to read, unsubscribe at any time.

Join 64,000 other subscribers.

TopicsAnthropicClaudeClaude Opus 5Claude Fable 5Pokemon RedCL-BenchStainlessLetta

StartupHub.ai Staff

Written by

StartupHub.ai Staff

Editorial team

The staff writers of StartupHub.ai, ranging from investment analysts to avid AI tool users, early adopters and critical enthusiasts. Backgrounds span engineering, business and the arts. We hold every piece to rigorous standards of research and review.

Daniel Singer

Written by

Daniel Singer

Editor, reviewed this article

Daniel Singer is an AI expert who has been writing about, covering and building AI technology since 2018.

Test your Agent Readiness now

Paste your website. How well ChatGPT, Claude and the other agents can read and use a site, in about a minute.

Watch

The videos behind the news, one flip at a time

The feed mixes the videos from our articles with startup demos and you flip through them like TV channels for free with no signup.