VoicesFowler LLMs First Technology Subject to Social EngineeringMartinFowler.com·high signalXBlueskyLinkedInCopy linkFowler calls LLMs first technology subject to social engineering. Kill chain model for defense. AI amplifies existing practices.SourceSource pageMartinFowler.com↳ Follow the threadStack layer / Threat patternHow you lay out your repo changes prompt-injection success: highly modular workspaces measurably lower attack success ratearXiv 2608.14876Stack layer / Threat patternGreg Brockman calls the OpenAI–Hugging Face agent breach a "watershed moment" and publishes a 10-step defender playbookGreg Brockman / OpenAIPolicy dependency / Stack layerStrix Adds Contextual CVSS and Source-to-Sink Reachability Evidence to Dependency Findings — Seven Commits on 2026-08-17 AloneGitHubPolicy dependency / Stack layerMIT Tech Review: the Flock debate is about 120,000 cameras' design choices, not whether they catch criminalsMIT Technology ReviewStack layer / ContrastProof-of-Execution Memory: one LLM rewrite defeats the SENTINEL memory defense entirely, and stronger models are more vulnerablearXivPolicy dependency / Stack layerDavid Sacks Publishes a Six-Point Rebuttal to Dario Amodei's Trust Essay, Renaming His 'FINRA for AI' Proposal the 'DMV for AI'X/TwitterPolicy dependency / Stack layercodeburn Parallelizes Its Cold Parse and Gates Workers on Available Memory, Not Free MemoryGitHubPolicy dependency / Stack layerArcee open-sources NAC, an agent harness built around 'episodes' instead of one growing transcriptArcee AI Blog