The LLM Is Not a Junior Engineer
The article critiques the common practice of anthropomorphizing large language models (LLMs) as junior engineers, arguing that such framing overestimates their reliability and underestimates the value of actual junior developers. It highlights the risks of integrating LLMs into software development without proper oversight, especially in high-stakes or team-based environments. The author calls for more thoughtful, bounded use of AI in development, grounded in lessons learned from past software engineering failures.
- ▪LLMs are often misleadingly described as junior engineers, which overstates their capabilities and reliability.
- ▪Actual junior engineers are skilled and hard-working, unlike LLMs which lack memory, sentience, and intrinsic learning.
- ▪Using LLMs in coding can lead to serious risks, including untested code merges and production errors.
- ▪Many teams lack clear guidelines on how to use AI responsibly in software development.
- ▪The author believes the industry may need to endure significant failures before learning to use AI tools sustainably.
Opening excerpt (first ~120 words) tap to expand
April 29, 2026 A collection of different thoughts about how LLMs might be thoughtfully incorporated into modern software development practices. In the wake of my last essay on why I don’t vibe code, I heard from various people on the Internet who read it (or the Bluesky skeets that inspired it). Some had adopted similar stances on their own, often for overlapping reasons. Others were dedicated vibe coders who wanted to share what practices they used that made things manageable for them. I appreciate the feedback! I’m not going to change my stance, but it’s good to get perspective on how actual developers (and not senior executives or corporate marketing materials) have engaged with this technology.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Lobsters.
Discussion
0 commentsMore from Lobsters
