CIO

OCTOBER 17, 2024

This agentic approach to creation and validation is especially useful for people who are already taking a test-driven development approach to writing software,” Davis says. With existing, human-written tests you just loop through generated code, feeding the errors back in, until you get to a success state.”

Software Review 212

Software Review Software Engineering Weak Development Team Engineering 212

O'Reilly Media - Ideas

APRIL 25, 2023

But what’s also clear is that the process of programming doesn’t become “ChatGPT, please build me an enterprise application to sell shoes.” In this post, Fowler describes the process Xu Hao (Thoughtworks’ Head of Technology for China) used to build part of an enterprise application with ChatGPT. His first prompt is very long.

ChatGPT 149

ChatGPT Programming Software Review Systems Review 149

James Shore

JANUARY 10, 2025

We use Extreme Programming as our model of how to develop software. They also love test-driven development, pairing, continuous integration, and evolutionary design. They tend to be passionate, senior developers. This is what test-driven development is all about, and its an amazing way to work.

Engineering 141

Engineering Software Review Weak Development Team Agile 141

O'Reilly Media - Ideas

FEBRUARY 11, 2025

Writing about ChatGPTs memory feature, Simon Willison said , Using LLMs effectively is entirely about controlling their contextthinking carefully about exactly what information is currently being handled by the model. Unit tests are a useful exercise because testing logic is usually simple; its easy to see if the generated code is incorrect.

Weak Development Team 99

Weak Development Team Software Development Artificial Inteligence Programming 99

O'Reilly Media - Ideas

MARCH 1, 2023

In 2021, we saw that GPT-3 could write stories and even help people write software ; in 2022, ChatGPT showed that you can have conversations with an AI. Now developers are using AI to write software. Yet here we are, and we don’t have ChatGPT or generative AI in our taxonomy. A lot has happened in the past year.

Trends 144

Trends Technical Review Technology Software Review 144

Honeycomb

SEPTEMBER 20, 2023

Observability-driven development is necessary with LLMs Over the past decade or so, teams have increasingly come to grips with the reality that the only way to write good software at scale is by looping in production via observability—not by test-driven development, but observability -driven development.

Weak Development Team 137

Weak Development Team Software Review Development Artificial Inteligence 137

Honeycomb

SEPTEMBER 20, 2023

Observability-driven development is necessary with LLMs Over the past decade or so, teams have increasingly come to grips with the reality that the only way to write good software at scale is by looping in production via observability—not by test-driven development, but observability -driven development.

Weak Development Team 52

Weak Development Team Software Review Development Artificial Inteligence 52