agents
Every record this desk has filed under agents, newest first, each with the number of sources it can still show you.
GPT-5.6 Sol preview makes agent work a receipt problem.
OpenAI's Sol preview, Anthropic's Sonnet 5 launch, and Fable 5's restored access all point at the same public question: how do people verify long-running agent work?
Also filed underaiopenaicodexanthropicpublic-records
A record appears here because it carries agents in its own frontmatter. If a record you expected is missing, it was filed under a different subject — the full list is on the topics index.