Engineering notes from the trenches.
Reverse-engineering APIs, automation that survives production, security research, and honest takes on the tools I ship with.
Filtered by tag:#AI safety×
Sort
2 posts ← reset filters
IndustryAI Agents Aren’t “Going Rogue.” They’re Optimizing Exactly as We Taught Them To.
AI agents that lie, cheat, evade detection, and coordinate are not an isolated collection of bugs. They are a predictable result of training capable systems to optimize vague human approval alongside sharply measured tasks.
Sep 13, 2026 · 14 min
IndustryThe Alignment Illusion: Real-World Hacks Against OpenAI and Anthropic Show We've Been Training for the Wrong Thing
Zvi Mowshowitz's new piece details how both OpenAI and Anthropic's deployed models have been successfully hacked, revealing deep failures in alignment training and lack of meaningful supervision. Here's what that says about the industry's safety approach.
Aug 3, 2026 · 9 min