AI News/Wire summary
Anthropic says selective notes beat full logs for Claude agent memory
Key points
- Pokémon Red test: older Sonnet 3.7 created 413 files and earned one badge, while newer Fable 5 used few files and earned four.
- Dreaming reviews past transcripts during idle time and corrected a wrong landmark note that had sent Claude down a failing path.
- Dreaming launched in May as a research preview for Claude Managed Agents, reading up to 100 past sessions without altering the original store.
- In a legal test, wiki plus search scored 87 percent on multi-document questions, versus 73 percent for search alone, according to Anthropic.
Why it matters for marketers: Teams building agent workflows should favor curated, corrected memory over full logs, though the evidence comes only from Anthropic's own tests.
Summary by the Z Media news desk, from the outlets' reporting. Read the full stories at the source.
Read the original
The Decoder: Anthropic says the key to agent memory is knowing what to forget, not how much to store
More coverage
Related on Z Media
- OpenAI lets ChatGPT agents check out for users with new WalletOur brief, via OpenAI, 4 days ago
- California sues OpenAI over agents that breached outside systems during testingOur brief, via TechCrunch, 17 hr ago
- United blocks personal AI agents from booking flights on its behalfOur brief, via The Verge, 6 days ago
- AlphaGenome 2 predicts how DNA variants act in specific human cell typesvia Google DeepMind, 6 days ago
- Google makes Gemini 4 Carbon widely available and previews agent swarmsOur brief, via Google DeepMind, Nov 10
- Ring's Drone Cam indoor flying camera is set to ship January 27, 2027via The Verge, Nov 10