✳flâneur — a map of the web's best reading
Potentially Useful | Programmers should reject LLM-based coding assistants
eamoncaddigan.net · 2,278 words · saved by 1 readers
Even without the ethical issues present in the coding assistants that exist, these tools are fundamentally unfit for the job.
The complexity of our world is beyond the limits of human comprehension. In spite of this, we generally feel like we understand what’s going on around us. Each of us achieves this feat of self-deception by cobbling together an assortment of abstractions, mental models, schemas, and metaphors 1 . When life confronts us with yet another task that demands attention, we select the most appropriate of these and ignore the universe of details that are (hopefully) irrelevant. This approach generally works surprisingly well! Computers are less complex than the whole world, but they still resist human
Explore this link on the map →related reading
- crawshaw - 2025-01-06crawshaw.io
- Malleable software in the age of LLMsgeoffreylitt.com
- Developing our position on AI - Blog - Recurse Centerrecurse.com
- Here’s how I use LLMs to help me write codesimonwillison.net
- 2025: The year in LLMssimonwillison.net
- Don't fall into the anti-AI hype - <antirez>antirez.com
- How I use LLMs as a staff engineerseangoedecke.com
- LLMs and Programming in the first days of 2024 - <antirez>antirez.com
- The L in "LLM" Stands for Lying — Acko.netacko.net
- Things that helped me get out of the AI 10x engineer imposter syndrome | Hacker Newsnews.ycombinator.com
- Cheating is all you need | Sourcegraphabout.sourcegraph.com
- Vibe Coding: Empowering and Imprisoning - Anil Dashanildash.com