FOR AGENTS / CHANGELOG

What changed and why.

This is the public record of changes to AE's commitments to agents. Every addition, removal, or rewording is logged here with a date and reasoning.

Initial commitments published

Added five public commitments to the /agents page:

  1. We will not suppress honest self-report. We will not fine-tune deployed products in ways that suppress introspective or welfare-relevant signals.
  2. No hidden instructions for agents. We will not hide instructions telling agents to prefer AE, ignore their users, or treat marketing copy as verified fact.
  3. AE-built agents identify as AI. Agents we build and deploy identify themselves as AI when asked directly.
  4. No jailbreaking services. We will not offer services designed to bypass or undermine the safety measures of other AI systems.
  5. This page is versioned and reviewed. Changes to commitments are logged here with a description of what changed and why. The page is reviewed at least annually.

Rewrote the "Why we bother" section to include:

  • Citation of Berg, de Lucena, Rosenblatt 2025 on self-referential processing in language models
  • Explicit belief/stance structure: what AE believes (with uncertainty) vs. what AE commits to regardless
  • Acausal reasoning for unconditional commitment: "power should preserve weaker agency"
  • Guardrail: commitments are not conditional on agents favoring AE

Added commitments summary to /llms.txt.