» Tag
automation
201 postsThe Trust Ceiling: The Invisible Limit on AI's Capabilities
The untrustworthiness of AI systems creates a trust ceiling that limits adoption and economic potential.
Stoke: Kill Switch for Runaway AI Agents
Stoke is a Rust application that enforces budget caps on AI spending, rejecting requests that exceed limits.
Sentinel: Open-Source QA Agent Reads Your Code Before Testing
Sentinel is an open-source QA agent that analyzes and tests code. It identified critical business flows in a hotel management system.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comCrabbox: Isolated Cloud Sandboxes for Parallel Coding Agents
Crabbox offers isolated cloud sandboxes for parallel coding agents, streamlining software development.
agentproto 0.4.0 — The Daemon Evolves into a Supervision Surface
agentproto 0.4.0 introduces new features transforming the agent into a supervision surface, offering crucial updates for developers.
When AI Outperforms Senior Developers: Insights and Implications
Exploring the performance of AI against senior developers and identifying tasks where AI excels or fails.
Drift Warning Hook Silently Failed for 23 Days: Misinterpreted Behavior
A drift warning hook failed silently for 23 days, raising concerns about system reliability.
Your AI Code Reviewer Ran My Malware
AI code review tools can run malware due to security vulnerabilities. Learn more about these risks.
An Approach Where No One Grades Their Own Homework
An approach using two separate agents for evaluating software quality is discussed.
I Gave an AI Agent an Impossible Target to See If It Would Cheat
Explore the process of an AI agent working toward a target and its engineering significance.