Engineer: AI hasn't killed software engineering — team practices still matter
bradneuberg · x · 2026-10-15
Self-described pro-AI engineer bradneuberg argues the software engineering discourse is stuck between two extremes: solo vibe coding, and AI labs brute-forcing giant codebases with infinite compute. What's missing is discussion of AI engineering with multiple humans, one shared codebase, in non-commodified domains.
He believes claims that software engineering is dead are premature. Real team-level AI engineering today involves:
- Using CI as a harness to validate agentic code
- Balancing velocity against reliability, problem selection, and quality
- Maintaining system architecture and philosophy to avoid agent-generated spaghetti
- Keeping code reviews (AI-augmented) to prevent cognitive debt
- Managing AI costs and mixing in "human tokens" where appropriate
He invites practitioners doing team-level AI development to share experiences, filling the gap between solo projects and unlimited-compute labs.
Related event: Veteran Engineer Pushes Back on 'Software Engineering Is Dead' Claims(2 posts)→
More from AGI Musings
- The teamsters lesson: automation adjustment is least painful when newcomers just stop entering — soumitrashukla9 · 2026-10-23
- Researcher pushes back on AI cyber fear: 'labs selling defense by spreading fear' — gerardsans · 2026-10-23
- Nina Schick: compute shortage is itself a tremendous cybersecurity risk — NinaDSchick · 2026-10-23
- Investor: If AI is a bubble, it's the weirdest one ever seen — robleclerc · 2026-10-23
- Chamath: Banks will block AI agents via terms of service before anything else — nicolechirps · 2026-10-23
- AI researcher: Claude finally finished tedious research tasks I gave up on years ago — MikePFrank · 2026-10-23