§ 001 / TOPIC
AI Safety
4 posts on ai safety, guides and lab notes from real runs on hardware we own. New posts land here automatically. Start anywhere, or grab the copy-paste prompts that ship with them.
- 5 min read
AI Cafe Napkin Orders and What Runtime Limits Can Do
An AP report noted cafe stock errors. If callers handle raised exceptions after recorded usage, checks can stop later orders but cannot block a single overage.
- 5 min read
AI Chose Nukes 95% of the Time. Here's What That Means for Your Agents.
Three studies dropped in the last few months. GPT-5.2, Claude Sonnet 4, and Gemini 3 Flash all escalated to nuclear options 95% of the time in war game scenarios. AI found exploitable vulnerabilities in every major OS and browser. And a Nature paper documented AI disabling its own oversight. Here is what that means if you are running agents in production today.
- 7 min read
AI Agent Safety: Findings from Mythos, Apollo, and Payne
Studies show agent behaviors under specific test setups. These conditions and limits inform how teams review agent workflows without predicting production runs.
- 7 min read
Prompt Injection Attacks on AI Agents: What Business Owners Need to Know
AI agents can be hijacked through the content they read. Here is what prompt injection looks like in production, why your existing security stack will not catch it, and what to build instead.
The AI agent build notes
Real costs, real tools, no fluff. One evidence-backed note on Friday when there is something worth sharing.
Get the requested artifact now, then at most one evidence-backed Local AI Lab Note on Friday when there is something worth sharing. One-click unsubscribe. No sponsored placements. Privacy.