Martin Fowler on delegating writing to LLMs
"As more people delegate writing to LLMs they will also delegate thinking and comprehension to LLMs. I don't want to do that, where's the fun of writing then?"
— Martin Fowler
Tags
10 posts tagged
"As more people delegate writing to LLMs they will also delegate thinking and comprehension to LLMs. I don't want to do that, where's the fun of writing then?"
— Martin Fowler
"When all is said and told, the "naturalness" with which we use our native tongues boils down to the ease with which we can use them for making statements the nonsense of which is not obvious."
— Edsger W. Dijkstra
LLM temperature controls how random the next token is. How temperature, top-p and top-k reshape the probabilities, and why Claude's API dropped them in 2026.
A system prompt is text placed before the conversation that sets a model's role and rules. See the raw chat template, its token cost and its limits.
ChatGPT Atlas puts an agent inside your browser. How prompt injection hides in page text, why filtering it fails, and where the real check has to live.
Structured output forces an LLM's reply to match a JSON schema by masking invalid tokens during decoding. JSON mode vs strict mode, with a runnable Python demo.
HyDE (hypothetical document embeddings) has an LLM write a fake answer, then searches with its embedding. How HyDE and query rewriting work, in Python.
ReAct is the agent pattern where an LLM alternates thoughts, tool actions and observations. What the 2022 paper showed, with a runnable Python ReAct loop.
Chain-of-thought prompting asks a model to write its reasoning before the answer. Why it works, when it helps, and how reasoning models changed it.
Prompt engineering is writing and testing the instructions you give an LLM. The techniques that still work in 2026, what changed, and a Python eval harness.