At a glance
- Relevance
- Practical value
- Warnings
- None
An experienced team that practices TDD and mob programming tried using AI for all their coding for 5 months. Their conclusion: it created fatigue, reduced flow, and was slower than doing it themselves.
LLM fatigue is a real risk for teams with complex, legacy codebases, not just a skill issue.
Summary
A team from a Norwegian bank that practices mob programming and TDD describes their 5-month experiment with Claude for all coding. They concluded that for their brownfield, domain-heavy systems, AI agents were simply not fast or accurate enough. The payoff from context-switching, waiting for responses, and manual
review was lower than just writing the code themselves. The hype around AI 'solving coding' ignores the complexity of legacy critical infrastructure. The team found LLMs excellent for analysis, dashboards, telemetry, and prototyping. The pain point is the 'sugar rush' effect: initial excitement leads to fatigue from
constant waiting and review. They explicitly state that AI-generated code reduces their understanding of the domain and breaks their flow. Their core finding is that the best use of LLMs is as an accelerator on well-architected codebases, not a replacement for human coding. The paper they mention
(published in the Journal of Systems and Software) details how to introduce new ways of working via low-commitment experiments. This is a practical, evidence-based counterpoint to the 'agents for everything' narrative. The tradeoff is clear: speed on simple tasks vs. quality and maintainability on complex systems.
Watch the video
This video is blocked due to your privacy settings. To watch this video, please accept YouTube marketing cookies.
Related breakdowns
AI Adoption: Maturity Matters More Than Speed for Engineering Teams
AI demands maturity, not speed. Teams must balance productivity with human collaboration, accountability, and ethical considerations.
Agent value can’t be measured by tokens — build verification first
If you can’t measure agent output, you can’t justify the spend. Use verification difficulty—not token cost—to choose AI agent use cases.
AI Makes Code Quality a Decision Problem, Not a Writing Problem
AI makes code generation easy, but shifts the hard part to decision quality. Teams must validate behavior, not authorship, and embed governance into…
Get TL;DW
Too Long; Didn't Watch.
A concise breakdowns of the AI and devtools videos that actually matter for engineering leaders.
Free. Weekly. No hype.
Video and thumbnails remain the property of their respective creators. tldw.news provides editorial analysis, commentary, and discovery links to original content.