{"url": "https://sub.xiliary.com/p/brendancodykenny/posts/22/whether-ai-is-reasonable-is-something-you-can-test-whether", "author": {"handle": "brendancodykenny", "name": "Brendan Cody-Kenny", "headline": "Technical Due Diligence for Software M&A", "url": "https://sub.xiliary.com/p/brendancodykenny"}, "post": {"id": 22, "url": "https://sub.xiliary.com/p/brendancodykenny/posts/22/whether-ai-is-reasonable-is-something-you-can-test-whether", "kind": "update", "summary": "Whether AI is reasonable is something you can test. Whether it is intelligent or creative is a debate that never ends.", "details": ["Intelligence and creativity are undefined enough that the debate never resolves. Reasonableness is closer to measurable.", "An LLM is trained on the sum of written human output, from the worst of the internet to Ulysses, so it has some claim to a centrist, averaging pull.", "Research is mixed: LLMs predict centrist politicians' votes better than fringe ones, but abstract questionnaires can pull them left.", "The mainstream a model gravitates to is itself shaped by training data and alignment choices, so it isn't neutral either."], "links": [], "tags": ["ai", "bias", "reasoning"], "happened_on": null, "created": "2026-09-30T11:15:28.714499Z", "edited": "2026-10-01T21:14:06.411299Z"}}