Current
·
C2
·2026-11
When AI Coding Agents Start Acting Like Tech Leads
The request: bump parser-rs from 1.1.0 to 1.3.0 in landing-rs. The agent added a mandatory assignment of its own and made it a condition of being done. I also remember a wider turn: a small request drifting toward rewriting a project until I stopped it. What infuriates me is not the mistake, it is the swap: the agent appointed its own goal, and I had to hand the original back. Work the agent invented is a different service.
Find Your Interest
- TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient
- Redesign how your team ships software with AI agents
- Android AI Tools: Vibe coding, sub-agents, and the Android CLI
- Q&A: What is agentic AI today, and what do we want it to be?
- Q&A: What is agentic AI today, and what do we want it to be?
- Introducing AI Code Agents: A TypeScript SDK to Solve Vendor Lock-in for Coding Agents
- Why your AI model could be a sleeper agent
- Your AI Agents Will Be Attacked. Red-Team Them First
- Why Docker Sandboxes Caught My Attention After ContainerDays Singapore
- JP Morgan and Hyundai Card Tests AI-Powered Payments Without Humans
Current
·
C2
·2026-11






