https://shadown.github.io/blog/tags/generative-ai/Recent content in Generative AI on shadown BlogHugoen-usThu, 03 Sep 2026 00:00:00 +0000https://shadown.github.io/blog/posts/2026-09-03_grok_bot_how-it-works/Thu, 03 Sep 2026 00:00:00 +0000https://shadown.github.io/blog/posts/2026-09-03_grok_bot_how-it-works/An architecture and mechanics walkthrough of `Grok Bot.app` (`com.anysphere.sand`, v0.18.0, Electron 42.1.0 / Chromium ~140, macOS arm64).https://shadown.github.io/blog/posts/2026-08-23_genai-security-silent-interface/Sun, 23 Aug 2026 00:00:00 +0000https://shadown.github.io/blog/posts/2026-08-23_genai-security-silent-interface/A comprehensive taxonomy of covert communication, exfiltration, and perception-abuse primitives available to autonomous adversaries, with a focus on the amplification effects of agentic AI.https://shadown.github.io/blog/posts/2026-08-22_pki-zero-trust-ai-agentic-infrastructure/Sat, 22 Aug 2026 00:00:00 +0000https://shadown.github.io/blog/posts/2026-08-22_pki-zero-trust-ai-agentic-infrastructure/LLM/GenAI agentic infrastructure must be zero-trust: every artifact, model, and runtime action is signed and verified in a tamper-evident chain to an HSM root. This design document specifies the PKI, identity, artifact signing, multi-agent validation, consumption, runtime signing, and audit planes.https://shadown.github.io/blog/posts/2026-08-18_genai-security-guide/Tue, 18 Aug 2026 00:00:00 +0000https://shadown.github.io/blog/posts/2026-08-18_genai-security-guide/LLM/GenAI threats & attack techniques · Secure Agents/Tools Development Guideline · Secure Agents/Tools Lifecycle