#agents (10)

A family of plain-text conventions at well-known paths that let machine readers understand how a site or repository wants to be read — the protocol surface of the Independent Internet.

Anthropic's disclosure of a state-sponsored espionage campaign in which an AI agent executed an estimated 80–90% of the operation with only sporadic human direction.

Anthropic's disclosure of a state-sponsored espionage campaign in which an AI agent executed an estimated 80–90% of the operation with only sporadic human direction.

Using folder structure — plain files in a well-organized hierarchy — as the orchestration mechanism for a multi-step AI workflow, instead of a code-level framework.

Van Clief and McDermott's paper arguing that a well-organized folder hierarchy can replace a multi-agent framework: the folder structure is the orchestration.

Van Clief and McDermott's paper arguing that a well-organized folder hierarchy can replace a multi-agent framework: the folder structure is the orchestration.

Karpathy's pattern for an LLM-maintained wiki: instead of re-deriving answers from raw documents on every query (RAG), the model integrates each source into a persistent, compounding knowledge base.

Karpathy's pattern for an LLM-maintained wiki: instead of re-deriving answers from raw documents on every query (RAG), the model integrates each source into a persistent, compounding knowledge base.

A persistent, interlinked knowledge base that a language model builds and maintains — integrating each source once, rather than re-deriving answers from raw documents on every query.

A web of machine-readable meaning where software agents can act on data, not just display it — the bridge toward Web 4.0.