Steve Yegge: I spend an hour a day hardening security in the agent era
Steve_Yegge · x · 2026-10-23
Steve Yegge reacts to warnings that AI agents will accelerate CVE discovery, calling the concern "terrifying but probably true."
He poses the dilemma: should developers abandon Node, Python and PHP entirely and vibe-code their own frameworks for security through obscurity? Even as an individual running a couple of agents, he now spends an hour a day on security hardening — and worries how exposed companies are right now.
More from coding & agent
- DAB, a cross-database agent benchmark, hits EMNLP Oral; best model only 38% pass@1 — adityagp · 2026-10-24
- 27B open-source model beats GPT-5.5 at computer tasks via evolved interfaces, at 1.5% the cost — alex_verem · 2026-10-23
- Interactive 3D AI server explainer built in one prompt with Claude and the open-source colorfigures skill — Promptmethus · 2026-10-23
- poem turns Codex sessions into chats — approve agent tasks from your iPhone — patrickreza · 2026-10-23
- Watching AI test your app like a real, picky customer — randal_olson · 2026-10-23
- Oxford paper draws TCP/IP lessons for securing and governing MCP and A2A agent protocols — sethlazar · 2026-10-23