83: Can You Trust Code Written Without AI? Agents, Security, and Software Careers in 2026

Can you trust software written without AI? We examine the risks of manual coding versus automated vulnerability exploits.At Rails World 2026, a show of hands revealed that writing material amounts of code by hand is becoming a rarity. We discuss whether that human-written code is actually safer, especially after reviewing the eMudhra certificate authority compromise where private keys were recovered in under a second. Between open-weight models demonstrating Mythos-class exploit skills and the ongoing debate over AI consciousness, the security landscape has shifted significantly.This conversation is for engineers navigating the reality of AI mandates at work and the impact of agents that continue running after you log off. We also cover the practical side of professional development, from Bethany building a holiday gift-list app to Brittany replacing cloud subscriptions with local transcription tools. By analyzing these technical shifts, we aim to help you maintain a grounded perspective on your career trajectory.Subscribe for weekly software engineering breakdowns, and comment on which professional challenge you want us to tackle next.

Hosts

• Overcommitted: https://overcommitted.dev
• Bethany Janos: https://www.trustyduck.dev
• Brittany Ellich: https://brittanyellich.com