Intelligence Feed
showing 30 items
Fragments: September 1
Martin Fowler · Software Engineering · src 8 · 2026-09-01T15:50:00-04:00 · HIGH 53
<p>Like many readers, I’m wary of AI generated prose. Simon Wilison has written an <a href="https://tools.simonwillison.net/llm-cliche-highlighter#https://martinfowler.com/articles/making-data-ready-for-agentic-ai.html">LLM cliché highlighter</a> - paste in some text, or a URL, and it will flag various patterns common to LLMs. It references a <a href="https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing">wikip
Fragments: September 16
Martin Fowler · Software Engineering · src 8 · 2026-09-16T16:05:00-04:00 · HIGH 53
<p>Reports of agentic hacking continue, in this case it happened back in May and it seems OpenAI did not disclose that they were responsible. <a href="https://simonwillison.net/2026/Sep/12/openai-agents-rubygems/">Simon Willison sees two options:</a></p>
<blockquote>
<ul>
<li>After the Hugging Face and Wiki attacks OpenAI were still unable to review their previous logs and determine that they had previously at
The Conductor Developer
Martin Fowler · Software Engineering · src 8 · 2026-07-31T09:48:00-04:00 · MEDIUM 48
<p class="precis"><b>TL;DR</b><br /><i>Why I think software development is starting to feel a little more like conducting an orchestra.</i></p>
<img src="https://martinfowler.com/rachels-ramblings/card.png" />
<p>There’s a shift happening in software development that I don’t think we’re talking about clearly enough.</p>
<p>For the last couple of years we’ve framed AI as a productivity tool. How much faster can it wr
I don't like LLMs
Martin Fowler · Software Engineering · src 8 · 2026-09-17T09:50:00-04:00 · MEDIUM 44
<p>I have a lot of mixed feelings about AI and LLM technology. I’m
fascinated by its effect on our profession, excited by the potential gains
in productivity - and thus the products we could rapidly build. On the other
hand, I’m fearful of the damage AI might cause: agent swarms taking over our
virtual and physical infrastructure, designing bio weapons. But, back on my
first hand, LLMs might also design miracle cures
Fragments: September 29
Martin Fowler · Software Engineering · src 8 · 2026-09-29T08:41:00-04:00 · MEDIUM 41
<p><a href="https://simonwillison.net/2026/Sep/24/harder/">Simon Willison:</a></p>
<blockquote>
<p>The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder</p>
<p>We can do amazing things with them, but unlocking their full potential requires extraordinary discipline and knowledge</p>
</blockquote>
<p>This has been a constant impression I get fro
Fragments: September 8
Martin Fowler · Software Engineering · src 8 · 2026-09-08T11:22:00-04:00 · MEDIUM 38
<p>Christian Catalini says we’re in a situation where we are <a href="https://catalini.com/ideas/economics-of-ai/">vastly reducing the cost of generating things, but not the cost of verifying them:</a>.</p>
<blockquote>
<p>This explains why the first major AI products appeared in chat, image generation, and code assistance. Not because these were the hardest human problems, but because their outputs were relativel
TDD inside the agent loop - theater or actual value?
Martin Fowler · Software Engineering · src 8 · 2026-08-11T07:39:00-04:00 · MEDIUM 26
<div class="img-link"><a href="https://martinfowler.com/articles/exploring-gen-ai/tdd-in-the-agent-loop.html"><img src="https://martinfowler.com/articles/exploring-gen-ai/donkey-card.png" width="" /></a></div>
<p>My colleagues at Thoughtworks tend to be big fans of Test-Driven
Development, and many people in the industry advocate telling LLM agents
to use TDD when building software. <b class="author">Bir
Fragments: October 4
Martin Fowler · Software Engineering · src 8 · 2026-10-04T23:28:00-05:00 · MEDIUM 26
<p>In response to my <a href="https://martinfowler.com/fragments/2026-09-29.html">last fragments</a> (probably the bit about us worrying if LLMs have consciousness when we when we should be wondering why they don’t have a conscience) <a href="https://x.com/metalanguage_os/status/2104934457333707058">“Metalanguage” replied</a>:</p>
<blockquote>
<p>we shipped the id and forgot the superego. classic software lifecycl
Fragments: August 18
Martin Fowler · Software Engineering · src 8 · 2026-08-18T11:04:00-04:00 · MEDIUM 23
<p>Part of the reason why I’m at Thoughtworks is because I’d like to see a software development organization founded on technical excellence as an example for the rest of the industry. The trouble is that I have little aptitude or inclination for the hard work of building such an organization. So I rely on working with people who are prepared to actually put the effort in. A key partner in all of this is <a href="htt
Making Your Data Ready for Agentic AI
Martin Fowler · Software Engineering · src 8 · 2026-08-27T09:11:00-04:00 · MEDIUM 23
<div class="img-link"><a href="https://martinfowler.com/articles/making-data-ready-for-agentic-ai.html"><img src="https://martinfowler.com/articles/making-data-ready-for-agentic-ai/card.png" width="350px" /></a></div>
<p>Lots of organizations are excited about what AI can do to streamline
their processes, save money, and juice margins. But AI's capabilities are
founded on the data that AI accesses, and f
An Accidental Blackboard
Martin Fowler · Software Engineering · src 8 · 2026-09-02T10:45:00-04:00 · MEDIUM 23
<div class="img-link"><a href="https://martinfowler.com/articles/exploring-gen-ai/an-accidental-blackboard.html"><img src="https://martinfowler.com/articles/exploring-gen-ai/donkey-card.png" width="" /></a></div>
<p><b class="author">Giles Edwards-Alexander</b> reports that during an
experiment to see how productive a team could be using fully agentic
engineering practices, the team accidentally prompted
Fragments: September 24
Martin Fowler · Software Engineering · src 8 · 2026-09-24T11:35:00-04:00 · MEDIUM 23
<p>Rob Bowley is “flipping tables in his head” with <a href="https://blog.robbowley.net/2026/09/18/the-ai-threat-is-real-it-just-isnt-the-one-in-the-headlines/">anger at the current media coverage of the danger of AI killing us all</a></p>
<blockquote>
<p>The risk I’m worried about isn’t a future machine deciding to wipe us out. It’s today’s AI, being wired into everything, carelessly and fast.</p>
</blockquote>
Fragments: August 4
Martin Fowler · Software Engineering · src 8 · 2026-08-04T08:08:00-04:00 · MEDIUM 20
<p>There’s been a fair bit of publicity of the <a href="https://www.theguardian.com/technology/2026/jul/22/openai-says-its-models-went-rogue-and-hacked-startup-in-unprecedented-incident">Open AI “rogue agent” that hacked into Hugging Face</a>. This prompted Anthropic to check what their models were up to and, to my complete lack of surprise, <a href="https://www.anthropic.com/news/investigating-incidents-cybersecurit
Fragments: August 24
Martin Fowler · Software Engineering · src 8 · 2026-08-24T11:29:00-04:00 · MEDIUM 20
<p>I was listening to <a href="https://www.nytimes.com/2026/08/18/opinion/ezra-klein-podcast-helen-toner.html">Ezra Klein’s interview with Helen Toner</a> about the recent OpenAI hack of Hugging Face and the subsequent discovery that there were swarms of agents inside OpenAI doing unsanctioned activities. One of the points Klein made was that at no point did any of these (thousands of?) agents ever try to check in wi
The Orchestrator's Tax
Martin Fowler · Software Engineering · src 8 · 2026-07-28T09:10:00-04:00 · LOW 8
<p>Subagents get justified by time saved and parallel execution, but
<b class="author">Rahul Garg</b> explains that's not what matters most. Every
token in the orchestrator's context is competing for its attention, and
the real value of a subagent is what it keeps out of that context.
Subagents should be treated as a tool for protecting the orchestrator's
working memory, offloading reaso
The Economic Benefit of Refactoring
Martin Fowler · Software Engineering · src 8 · 2026-07-30T09:04:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/exploring-gen-ai/refactoring-economic-benefit.html"><img src="https://martinfowler.com/articles/exploring-gen-ai/donkey-card.png" width="" /></a></div>
<p><b class="author">Giles Edwards-Alexander</b> does an experiment to see if decomposing a
large function helps reduce token costs, suggesting that is may now be
possible to measure the eco
Practitioner Voice: The Writing Category Nobody has Named Yet
Martin Fowler · Software Engineering · src 8 · 2026-08-19T14:15:00-04:00 · LOW 8
<p><b class="author">Jim Highsmith</b> recognizes that effective writing from a practitioner is
a style distinct from academic writing or thought-leadership content. It's
a style that I advocate, and my contributors mostly follow. Jim decided it
was important to give it a name, and identify what makes it distinctive.</p>
<p><a class="more" href="https://martinfowler.com/articles/practitioner-voice.
Citizens Build, Agents Execute, Experts Govern
Martin Fowler · Software Engineering · src 8 · 2026-08-19T14:30:00-04:00 · LOW 8
<p class="precis"><b>TL;DR</b><br /><i>Why building an app over the weekend isn't the same as building enterprise software</i></p>
<img src="https://martinfowler.com/rachels-ramblings/card.png" /><p>I’ve noticed an interesting gap opening up over the last six months. It isn’t really a gap in technology. It’s a gap in what different people think software engineering actually is.</p>
<p>The conversation usually starts
Maybe We Shouldn't Be Reviewing All This Code
Martin Fowler · Software Engineering · src 8 · 2026-09-02T09:32:00-04:00 · LOW 8
<p class="precis"><b>TL;DR</b><br /><i>Or, perhaps the problem isn't that AI has broken code review, maybe it’s that we've been using code review to solve the wrong problems</i></p>
<img src="https://martinfowler.com/rachels-ramblings/card.png" /><p>I was on a panel recently with Brian Houck from DX at Code Remix, hosted by Moderne. It was one of the more interesting panels I’ve done, largely because we disagreed. As
Bliki: Paracelsus Maxim
Martin Fowler · Software Engineering · src 8 · 2026-09-02T18:03:00-04:00 · LOW 8
<p><b>The difference between a medicine and a poison is dosage.</b></p>
<p>Often we talk about certain habits, in programming or life, are good or
bad. But few things are simple binaries. Some vary with context: reading a
book is a good thing sitting in my garden, but not while driving my car. But
another variable is dosage: a little pain-killer salves my headache, but too
much will kill me.</p>
<p>The impo
Do you even need a presentation?
Martin Fowler · Software Engineering · src 8 · 2026-09-08T09:42:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/never-send-slides/need-presentation.html"><img src="https://martinfowler.com/articles/never-send-slides/index/card.png" width="" /></a></div>
<p>Like me, <b class="author">Sumeet Gayathri Moghe</b> is tired of poor
presentations with bad slide decks. He's started to write a series of
posts on how to avoid these calamities, beginning with a
Social Media Engagement: summer 2026
Martin Fowler · Software Engineering · src 8 · 2026-09-09T12:21:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/2026-social-traffic.html"><img src="https://martinfowler.com/articles/2026-social-traffic/card.png" width="350px" /></a></div>
<p>A quick survey of recent engagement of my posts on social media, indicating which
service has by far the most engagement, and which service has seen a
precipitous decline since early 2025.</p>
<p><a class="more"
Nail the Narrative
Martin Fowler · Software Engineering · src 8 · 2026-09-15T11:11:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/never-send-slides/nail-your-narrative.html"><img src="https://martinfowler.com/articles/never-send-slides/index/card.png" width="" /></a></div>
<p><b class="author">Sumeet Gayathri Moghe</b> finds many folks building
presentations get tangled in building slides without a coherent narrative.
He advises distilling the big idea, visualizing th
Healthy Feedback
Martin Fowler · Software Engineering · src 8 · 2026-09-24T10:10:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/healthy-peer-feedback.html"><img src="https://martinfowler.com/articles/healthy-peer-feedback/card.png" width="350px" /></a></div>
<p>Human collaboration, like most things, improves with feedback. But it's
not obvious how to make feedback effective. <b class="author">Anuja Karnik</b>
and <b class="author">Sumeet Gayathri Moghe</b> pass on a
Bliki: Sensible Default
Martin Fowler · Software Engineering · src 8 · 2026-09-29T09:43:00-04:00 · LOW 8
<p>A Sensible Default is a practice that, absent some overriding context,
should be used when carrying out a certain kind of task. In software
development such sensible defaults might include things like “use version
control”, “separate UI logic from domain logic”, “automate deployment
pipelines”.</p>
<p>The term “sensible default” is a deliberate contrast to “best practice”.
Folks dislike calling things “
Principles for effective slides
Martin Fowler · Software Engineering · src 8 · 2026-09-30T10:14:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/never-send-slides/slide-principles.html"><img src="https://martinfowler.com/articles/never-send-slides/index/card.png" width="" /></a></div>
<p>Not every presentation needs slides, but when they earn their place,
they work as a visual channel that complements the speaker rather than
replacing them. <b class="author">Sumeet Gayathri Moghe</b
Are Harnesses Worth the Cost?
Martin Fowler · Software Engineering · src 8 · 2026-10-13T09:35:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/are-harnesses-worth-the-cost.html"><img src="https://martinfowler.com/articles/exploring-gen-ai/donkey-card.png" width="" /></a></div>
<p><b class="author">Naresh Jain</b> compares coding agents building the same
API service with and without a behavioral harness. A frontier model, GPT-6
Sol, passed every external evaluation either way. But
The Craft of Practitioner Voice
Martin Fowler · Software Engineering · src 8 · 2026-10-13T10:06:00-04:00 · LOW 8
<p>A couple of months ago <b class="author">Jim Highsmith</b> explained how
practitioners writing for each other forms a distinct style of writing. He
now adds a section to the article with more detail on the craft of how we
write in this style. How the writer shows up in the prose, its four
principles, the role of story, how to sensibly use AI, three levels of
editing, and clarity of th
Build your slide template
Martin Fowler · Software Engineering · src 8 · 2026-10-14T10:20:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/never-send-slides/build-your-slide-template.html"><img src="https://martinfowler.com/articles/never-send-slides/index/card.png" width="" /></a></div>
<p>Building a slide template starts with three foundational choices —
colours, fonts and layouts. <b class="author">Sumeet Gayathri Moghe</b> covers
the basics of color theory and how t
When Software Meets Hardware
Martin Fowler · Software Engineering · src 8 · 2026-10-15T09:25:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/software-meets-hardware.html"><img src="https://martinfowler.com/articles/software-meets-hardware/card.png" width="" /></a></div>
<p>When software meets hardware, engineering principles remain largely the
same, but the sensible defaults often change. <b class="author">Kuldeep Singh</b>
describes our experience modernizing a large IoT fleet of b