Original post on rollenspiel.social

LLM Code Generation and Token Waste: How Built-in Runtime Features Can Cut Costs

The article explores the tension between LLM-generated code and token costs, specifically how AI models like Claude waste output tokens by r

Why AI coding tools can help you write better code, not just faster code

The article argues that AI coding tools (LLMs) can be used not just for rapidly producing low-quality code ("slop"), but also for writing hi

Why AI coding tools can help you write better code, not just faster code

The article argues that AI coding tools (LLMs) can be used not just for rapidly producing low-quality code ("slop"), but also for writing hi

Reflections on LLMs and Their Impact on Software Development Practices

The author shares personal reflections on the current state of Large Language Models (LLMs) and AI in software development, questioning whet

Fine-Tuning LLMs Is a Waste of Time

Examining the Compiler Analogy: Are LLMs the Next Evolution in Programming Abstraction?

The article explores the debate around whether Large Language Models (LLMs) are similar to compilers and whether we're moving toward a world

Why reviewing AI-generated code is more expensive than writing it

The article discusses how LLMs (large language models) approach code generation differently from humans. Unlike human developers who instinc