https://kre80r.com/tags/api/Recent content in Api on /sys/admin/blogHugoenFri, 16 Oct 2026 00:00:00 +0000https://kre80r.com/is-it-really-opus/Fri, 16 Oct 2026 00:00:00 +0000https://kre80r.com/is-it-really-opus/<p>In August Anthropic said they will put <a href="https://techcrunch.com/2026/08/11/anthropic-says-it-will-watermark-text-generated-by-its-ai-models/">invisible watermarks</a> in text written by Claude, a hidden pattern that only their own tools can detect. In October <a href="https://techcrunch.com/2026/10/05/openai-will-start-watermarking-chatgpts-text-in-the-eu/">OpenAI said the same for the EU</a>. So the labs want to know which text came from their models. My first thought was, OK, can we do the opposite? Send some requests to an API, look at what comes back, and know which <strong>model</strong> is behind it.</p>