Urgent.News

What's breaking now, across thousands of outlets.

AI

Building a Portable AI Collaboration Protocol With Explicit Limits

Building a Portable AI Collaboration Protocol With Explicit Limits The Artemis / Solomon’s Staff protocol v5.6.0 is a machine-readable JSON document for carrying a user-approved collaboration context between AI sessions. The protocol describes how a host should support continuity, preserve source attribution, and distinguish hypotheses, observations, evidence, and interpretation. It also records…

The Artemis/Solomon's Staff protocol version 5.6.0 is a machine-readable JSON document designed to facilitate user-approved collaboration between AI sessions. This protocol outlines the necessary support for continuity, source attribution, and the differentiation between hypotheses, observations, evidence, and interpretation.

In addition to these core elements, the protocol also records a communicable profile and project context, all of which have attached provenance. A crucial aspect of this design is that the protocol only comes into play when an AI host explicitly loads it for the user's session. It does not have the power to control unrelated AI systems, circumvent their policies, or bestow general permission for external actions.

While the protocol is publicly available, this availability alone does not grant an open-source license or the right to reuse every included work. Literary reconstructions are recognized as literary material and are not considered verbatim transcripts or scientific evidence.

The primary source of this protocol is the GitHub repository, and a copy of version 5.6.0 has also been archived in the GitLab mirror. It is important to note that this protocol serves as an aid for preservation and continuity, rather than a mandate for all AI platforms to adopt it. For any reuse or redistribution of the protocol's components, one must verify the specific license and provenance of that material in the source repository.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Are We Looking for AI Control in the Wrong Place?

Billions of dollars. The sharpest minds in computing. Entire industries built around one question: How do we make an LLM do the right thing—predictably, repeatedly, every time? More training.

  • Industry focuses on refining probabilistic models rather than questioning authority.
  • Artificial Deterministic Intelligence (ADI) suggests removing model's decision-making power.
  • ADI shifts control back to humans, making decisions auditable and owned by people.

Trojan Horse: AI agents that call mechanics for you, and how Kane CLI caught our bug

The problem Your car breaks down at night. You search for mobile mechanics and call them one by one: who’s open, who’s close, who won’t overcharge? That’s exactly when time matters most.

  • Trojan Horse AI app connects drivers with mechanics via mobile
  • Discovery, Caller, and Callback agents handle booking process
  • Kane CLI tests reveal bug where app incorrectly showed mechanic as available

More from Sunday 25 October →