Yesterday, Anthropic just released the API for this Dream, which is really fascinating. What it does is let the Claude agent "dream" on its own, organizing the memories it wrote down in past sessions—merging duplicates, updating expired ones, unifying contradictions, and even
TOOLS
-
Epstein suicide note OCR benchmark test results
By
–
Epstein Suicide Note OCR Benchmark test: 1. Gemini 85%
2. GPT-5.5 82%
3. Grok 4.3 80%
4. Opus 4.7 75% -
Improving Agent Error Messages and Document Creation Endpoint
By
–
Ah weird, we should have better error messages for the agent. It should just create a new doc via the share markdown endpoint If you point it at http://
proofeditor.ai/agent-docs it’ll know what to do and can install a skill -
People can quit and run their own business using technology
By
–
They can quit and work somewhere else. Or run their own business, like I do. Where they would be idiots not to use this technology themselves. 🙂
-
Agent Observability: Storing Feedback with Traces for Learning Systems
By
–
Hot take, the models are not going to converge in the way that most folks talk about
-
AI paper listing service with open API access
By
–
Mine makes lists of all the AI papers. No barrier on the API. 🙂
-
The Agentic Era Begins: Discover Cutting-Edge AI Tools
By
–
We're seeing major advances vs pancreatic cancer. Today @NEJM data for daraxonrasib @RevMedicines https://
nejm.org/doi/full/10.10
56/NEJMoa2505783?query=featured_home
…
Context for this first-in-class molecular glue https://
nejm.org/doi/full/10.10
56/NEJMoa2505783?query=featured_home
… -
AI Model Analogy: Hermes vs. OpenClaw
By
–
I LOVE @garrytan
's analogy: "
@NousResearch
's Hermes is a beautiful brand new reliable Honda and @OpenClaw is a Ferrari that you need to bring a wrench for when it breaks down on the side of the road"