Software Should be Free

Inspired by https://www.justfivemins.com/p/episode-146-christmas-day-2025-edition

happy xmas!

FOSS projects this year of 2025:

- https://github.com/timabell/disk-hog-backup
- https://github.com/timabell/gitopolis
- https://github.com/timabell/markdown-neuraxis

- It was "Comprehension Debt" not "Cognitive Debt" - close!

# Summary

In this conversation, Tim Abell and David Sheardown explore the challenges and innovations in productivity tools and AI coding assistants and the overwhelming landscape of AI tools available for software development.

The dialogue delves into the nuances of using AI in coding, the potential of multi-agent systems, and the importance of context in achieving optimal results.

They also touch on the future of AI in automation and the implications of emerging technologies.

# Takeaways

1. AI is reshaping the workplace, requiring adaptation from professionals.
2. Understanding engineering problems requires a structured approach.
3. AI coding tools are rapidly evolving and can enhance productivity.
4. Providing clear context improves AI coding results.
5. Multi-agent systems can coordinate tasks effectively.
6. The landscape of AI tools is overwhelming but offers opportunities.
7. Understanding the limitations of AI tools is crucial for effective use.
8. Innovations in AI are making automation more accessible.
9. It's important to balance AI use with traditional coding skills.
10. The future of AI in software development is promising but requires careful navigation.

# Full details

In this episode of Software Should Be Free, Tim Abell and David Sheardown delve into the rapidly evolving landscape of AI-powered coding assistants. They share hands-on experiences with various AI coding tools and models, discuss best practices (like providing clear project context vs. “vibe coding”), and outline a mental model to categorize these tools. Below are key highlights with timestamps, followed by a comprehensive list of resources mentioned.

Episode Highlights

• 00:05 – Introduction: Tim expresses feeling overwhelmed by the proliferation of AI coding tools. As a tech lead and coder, he’s been trying to keep up with the hype versus reality. The discussion is set to compare notes on different tools they’ve each tried and to map out the current AI coding assistant landscape.
• 01:50 – Tools Tried and Initial Impressions: David shares his journey starting with Microsoft-centric tools. His go-to has been GitHub Copilot (integrated in VS Code/Visual Studio), which now leverages various models (including OpenAI and Anthropic). He has also experimented with several alternatives: Claude Code (Anthropic’s CLI agentic coder), OpenAI’s Codex CLI (an official terminal-based coding agent by OpenAI), Google’s Gemini CLI (an open-source command-line AI agent giving access to Google’s Gemini model), and Manus (a recently introduced autonomous AI coding agent). These tools all aim to boost developer productivity, but results have been mixed – for example, Tim tried the Windsurf editor (an AI-powered IDE) using an Anthropic Claude model (“Claude 3.5 Sonnet”) and found it useful but “nowhere near 10×” productivity improvement as some LinkedIn influencers claimed. The community’s take on these tools is highly polarized, with skeptics calling it hype and enthusiasts claiming dramatic gains.
• 04:39 – Importance of Context (Prompt Engineering vs “Vibe Coding”): A major theme is providing clear requirements and context to the AI. David found that all these coding platforms (whether GUI IDE like Windsurf or Cursor, or CLI tools like Claude Code and Codex) allow you to supply custom instructions and project docs (often via Markdown) – essentially like giving the AI a spec. When he attempted building new apps, he had much more success by writing a detailed PRD (Product Requirements Document) and feeding it to the AI assistant. For instance, he gave the same spec (tech stack, features, and constraints) to Claude Code, OpenAI’s Codex CLI, and Gemini CLI, and each generated a reasonable project scaffold in minutes. All stuck to the specified frameworks and even obeyed instructions like “don’t add extra packages unless approved.” This underscores that if you prompt these tools with structured context (analogous to good old-fashioned requirements documents), they perform markedly better. David mentions that Amazon’s new AI IDE, Kiro (introduced recently as a spec-driven development tool) embraces this “context-first” approach – aiming to eliminate one-shot “vibe coding” chaos by having the AI plan from a spec before writing code. He notes that using top-tier models (Anthropic’s Claude “Opus 4” was referenced as an example, available only in an expensive plan) can further improve adherence to instructions, but even smaller models do decently if guided well.
• 07:03 – Community Reactions: The conversation touches on the culture around these tools. There’s acknowledgment of toxicity in some online discussions – e.g. seasoned engineers scoffing at newcomers using AI (“non-engineers” doing vibe coding). Tim and David distance themselves from gatekeeping attitudes; their stance is that anyone interested in the tech should be encouraged, while just being mindful of pitfalls (like code quality, security, or privacy issues when using AI). They see value in exploring all levels of AI assistance, provided one remains pragmatic about what works and stays cautious about sensitive data.
• 29:57 – Models + 4 Levels of AI Coding Tool: Tim introduces a mental model to frame the AI coding assistant ecosystem (around 29:57). The idea is to separate the foundational models from the tools built on top, and to classify those tools into four levels of increasing capability:
  • Underlying Models: First, there are the core large language models themselves – e.g. OpenAI’s GPT-4, Anthropic’s Claude (various versions like Claude 1.* and 2, including fast “Sonnet” models and the heavier “Opus” models), Google’s Gemini model, as well as open-source local models. These are the engines that power everything else, but interacting with raw models isn’t the whole story.
  • Level 1 – Basic Chat Interface: Tools where you interact via a simple chat UI (text in/out) with no direct integration into your coding environment. ChatGPT in the browser, or voice assistants that can produce code snippets on request, fall here. They can write code based on prompts, but you have to copy-paste results – the AI isn’t tied into your files or IDE.
  • Level 2 – Agentic IDE/CLI Assistants: Tools that deeply integrate with your development environment, able to edit files and execute commands. This includes AI-augmented IDEs and editors like Windsurf Editor (a standalone AI-native IDE) and Cursor (AI-assisted code editor), as well as command-line agents that can manipulate your project (like the CLI versions of Claude Code, OpenAI Codex, or Gemini CLI). At this level, the AI can read your project files, make changes, create new files, run build/test commands, etc., acting almost like a pair programmer who can use the keyboard and terminal. (For example, Windsurf’s “Cascade” agent mode and Cursor’s agent mode allow multi-file edits and running shell commands automatically.)
  • Level 3 – Enhanced Context and Memory: Tools or techniques focused on feeding the model more project knowledge and context (sometimes dubbed “context en...

Tim & Jim discuss what they've learned trying to use AI tools such as github, gpt, windsurf, claude etc to write code in small and large projects, open and closed source.

• Jim: luxagen.com
  • RotKraken
  • rkd
• Vibe coding obama meme
• David just5mins
• Windsurf referer link for bonus credits
• cursor vs windsurf

From the blog - https://0x5.uk/2025/01/31/why-is-reading-bad-code-so-painful/

David's  just-five-mins podcast - https://www.justfivemins.com/

ps, when I said "Increased heart attack" I meant to say "Increased heart rate" 🤕 😆 - but maybe bad code does lead to increased heart attack, so a Freudian slip?!

A piece on leadership and teams needed to create great software projects and overcome the organisational immune system, all without any fan noise, and an intro from Mark.

• Unicorn project book
• DevOps handbook (hint, DevOps is *not* a separate team or job title, that's just Ops)
• Culture - The Fearless Organisation book
• MeLE Fanless Mini PC Quieter 4C
• Dead Sea Effect

A flowing discussion with Neil about the life of a contractor, before during and after, with some important mental health lessons hard learned along the way. Neil shares advice for people at every stage in the contracting journey, from tentative first steps to options for going beyond contracting, along with his own journey.

• Neil: https://www.neilmillard.com/
  • LinkedIn https://www.linkedin.com/in/neilmillard/
  • Youtube https://www.youtube.com/@confidentcontractor
• The new book: https://www.confident-contractor.co.uk/ - book out 24th July 2024
  • https://www.amazon.co.uk/Confident-Contractor-Thriving-Contracting-beyond-ebook/dp/B0D8QFHBZ1 - preorder now - early bird kindle price of 99p 
• https://www.theministryofinspiration.com/
• https://rethinkpress.com/books/how-to-write-your-book-without-the-fuss/

Share this episode: https://share.transistor.fm/s/26ea1cb5

Also in the episode:

• Self publishing a book with ReThink press - the backstory
• The varied journeys into IT and contracting
• Impostor syndrome for permies and contractors alike.
• CapEx vs OpEx

David kindly had me on as a guest on his wonderful "just 5 mins" show to talk a bit more about outside-in-testing and answer some of his questions after my last episode on this show on the matter.

- Just Five Mins! Episode 78 - Outside in Testing with Tim

A follow up to my blog post on test automation - with an angle that I think is missing in so much of the software industry - outside in fully automated tests from the perspective of the user is THE most important thing - plus don't let your tests see your internals, not even for setup and teardown.

• (01:53) - automated tests blog

• timwise.co.uk/2024/01/13/new-tool-sln-items-sync-for-visual-studio-solution-folders/
• justfivemins.com (David's podcast)
• buttondown.email
• timwise.co.uk/subscribe

• https://timwise.co.uk/2023/10/20/use-kdiff3-for-merge-conflict-resolution/
• https://timwise.co.uk/2023/10/20/git-what-do-'base'-'local'-'remote'-mean/
• https://timwise.co.uk/2023/09/28/what-is-hexagonal-architecture/
• https://timwise.co.uk/2019/10/14/merge-vs-rebase/
• https://timwise.co.uk/subscribe/
• https://github.com/rustworkshop/gitopolis/tree/3a8eb6e868a4e42370e8f4d587ad0e8525e9da2e/tests