https://ashwinviswamithiran.com/tags/stix/Recent content in Stix on Ashwin Viswamithiranhttps://ashwinviswamithiran.com/og-default.pnghttps://ashwinviswamithiran.com/og-default.pngHugoen-usWed, 30 Sep 2026 00:00:00 +0000https://ashwinviswamithiran.com/writing/it-reads-better-than-it-decides/Wed, 30 Sep 2026 00:00:00 +0000https://ashwinviswamithiran.com/writing/it-reads-better-than-it-decides/Building an OpenCTI enrichment connector on Gemini: where the model was genuinely good, where it would have done real damage, and the six times running it made me move a decision out of the model and into deterministic code.https://ashwinviswamithiran.com/writing/weve-seen-this-movie-before/Mon, 24 Aug 2026 00:00:00 +0000https://ashwinviswamithiran.com/writing/weve-seen-this-movie-before/Prompt attacks are new. The tooling being built around them is not. It's the same ladder malware defence climbed over twenty-five years, being climbed again in a handful.https://ashwinviswamithiran.com/writing/teaching-a-chatbot-to-read-a-spider-web/Thu, 09 Apr 2026 00:00:00 +0000https://ashwinviswamithiran.com/writing/teaching-a-chatbot-to-read-a-spider-web/Why a capable AI assistant could not answer an easy question about a well-documented threat actor, and the unglamorous fix: flattening a threat-intelligence graph into one readable card per entity, ahead of time.