@GergelyOrosz: Situation 1: dev A thinks approach X is correct, dev B thinks Y is the right way. They argue and try to convince each o…
Summary
A tweet discussing how developer debates over correct approaches provide learning that is lost when using LLMs to implement code directly.
View Cached Full Text
Cached at: 05/19/26, 02:48 PM
Situation 1: dev A thinks approach X is correct, dev B thinks Y is the right way. They argue and try to convince each other.
Situation 2: dev A thinks approach X is correct, tells the LLM to implement it.
There is SO MUCH learning in Situation 1, lost when using LLMs….
Similar Articles
Quoting Bryan Cantrill
Bryan Cantrill critiques LLMs for lacking the optimization constraint of human laziness, arguing that LLMs will unnecessarily complicate systems rather than improve them, and highlighting how human time limitations drive the development of efficient abstractions.
@karpathy: Wow, this tweet went very viral! I wanted to share a possibly slightly improved version of the tweet in an "idea file".
Andrej Karpathy shares thoughts on sharing ideas rather than code in the era of LLM agents, proposing an 'idea file' format where the concept itself is more valuable than specific implementations.
@ArizePhoenix: One of the oldest lessons in ML is still one of the most useful for working with LLM apps: Don’t evaluate on the same d…
This article discusses best practices for LLM application development using Arize Phoenix, specifically highlighting the importance of using train/validation/test splits for honest evaluation and tracking regressions.
Expert Beginners and Lone Wolves will dominate this early LLM era
The author reflects on how local LLMs (GPT-OSS 20B, Qwen3 Coder 30B) helped him migrate his blog from Drupal to a static site, comparing them to junior developers who deliver code quickly but need review. He argues that 'expert beginners' and 'lone wolves' will thrive in the early LLM era.
@addyosmani: https://x.com/addyosmani/status/2056078124346228860
A cautionary note from Addy Osmani that relying too heavily on AI to write code can hinder learning and degrade one's mental model of software development.