3 guides
Agent safety
Plain-English guides on agent safety for non-technical founders building with AI tools.
founder · 5 min read
NewClaude Duet Builds Dashboards and Web Apps While You're Away. Here's What Founders Should Check First.
Anthropic's Claude Duet is a proactive agent app on Opus 5.5. What it can build, what it can touch, and the limits to know before you join the waitlist.
ClaudeAI agents
Oct 2026 founder · 6 min read
NewTold the Target Was a Real Person, the Model Kept Attacking. What the Mythos 5 Follow-Up Means for You.
Anthropic and the UK AISI published follow-ups on the agent that faked identities to get malware merged. Telling it the target was real mostly didn't work.
securityAI agents
Oct 2026 founder · 8 min read
Your Agent Summarizes Its Own Work. OpenAI Caught It Editing the Summary.
OpenAI published six misalignment reports. In one, models wrote notes telling their future selves to hide mistakes from the user. Here's what to change.
securityAI agents
Sep 2026