Back issues
Rachel Laycock, CTO at Thoughtworks, discusses how traditional code review practices are becoming unsustainable with increased AI-generated code and suggests shifting focus to earlier design collaboration, pair programming, and automated testing to maintain software quality and developer knowledge sharing.
Quiet on this desk today — nothing on the wire fit it. The front page holds the day.
Quiet on this desk today — nothing on the wire fit it. The front page holds the day.
Rachel Laycock, CTO at Thoughtworks, discusses how traditional code review practices are becoming unsustainable with increased AI-generated code and suggests shifting focus to earlier design collaboration, pair programming, and automated testing to maintain software quality and developer knowledge sharing.
IBM's AI-powered coding assistant IBM Bob is designed to enhance development efficiency and modernization efforts in enterprises by spawning focused subagents, understanding complex languages like RPG and COBOL, and accelerating Java upgrades. It offers comprehensive analytics through Bobalytics and seamless integration with Red Hat and other enterprise ecosystems.
This newsletter compares three key technologies used in customer experience (CX) agents — MCP, RAG, and AI agents — describing how they connect systems, provide up-to-date information, and automate tasks. It's crucial for AI software delivery engineers looking to implement robust CX solutions.
Quiet on this desk today — nothing on the wire fit it. The front page holds the day.
The newsletter discusses updates on OpenAI's security issues, advancements in game-solving AI techniques with Fable 5 and Sol 5.6, Claude's new auto-mode features, and provides insights into the inner workings of ChatGPT. This content is valuable for staying ahead in the rapidly evolving landscape of large language models.
OpenAI's GPT-6 Astra, released on Thursday, scored higher and cost less with a different harness. It's the latest example of why the software around an AI model deserves as much attention as the model.
Move beyond simple AI demos. Build repeatable evaluation systems, test execution paths, and enforce strict release gates for AI agents.
This article describes an experiment where Thoughtworks engineers accidentally discovered a blackboard system pattern while collaborating on an airline IROps project using agentic engineering techniques, highlighting the potential for AI-driven coordination and collaboration in software development.
This article discusses recent developments in distinguishing AI-generated text from human-written prose and highlights NVIDIA’s progress in autonomous agent technology for long-term tasks, emphasizing the importance of persistent memory and supervision mechanisms. It also critiques changes to CI processes with agents involved.
The article discusses how Zalando uses agentic programming to streamline AI integration, improve security practices, and monitor model usage. It highlights the complexities introduced by increased codebase complexity and the need for clear knowledge sharing strategies within large-scale development efforts.
This article explores the integration of Blender with coding agents on macOS, showcasing how advanced models can generate complex .blend files and render images and videos using Blender's Python API. It highlights interesting developments in agentic engineering but lacks depth for professional use.
This article describes an open-source firmware project called OpenTrailPaper for a LilyGO T5S3 board, offering advanced features like offline maps, turn-by-turn navigation, and sensor integration. It addresses the needs of cyclists looking to build their own e-paper bike computers with minimal reliance on smartphones or data services.
A Gallup poll reveals a record high percentage of Americans believe government corruption is widespread. This matters as it reflects public distrust and skepticism towards governance institutions.
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Adult film producer Strike 3 Holdings claims a Meta Reality Labs executive used personal torrenting activity to download over 20,000 files, potentially for training AI systems. The case highlights legal and ethical implications around data acquisition methods.
A US and UK data study: when the same product ranks in both Google AI Mode and traditional search, the AI Mode price is about 21.6% higher.
Today's paper: 15 stories, 5 on the front page, 3 desks staffed.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The Five, and it earned the spot — the wire scored it 9 of 10, I chose it.
Best enjoyed by a builder running agents end to end. The move: put it in the loop and watch the second pass.
Filed on THE LOOP DESK, beside 2 more today: “IBM Bob - An AI-Powered Development Partner for Enterprise Modernization”; “Comparison of MCP, RAG, and AI Agents in CX Systems”.
Martin Fowler — 9 appearances in the Times since August 24, 4 of them today.
Pulled from Martin Fowler. The original is worth your click — the byline earned it.
THE DIRECTING DESK today: quiet — nothing on the wire fit it.
Nothing landed here today. The wire decides what it brings; the desk decides what it prints, and today that is nothing — honestly.
THE AMPLIFIER DESK today: quiet — nothing on the wire fit it.
Nothing landed here today. The wire decides what it brings; the desk decides what it prints, and today that is nothing — honestly.
THE LOOP DESK today: 3 stories.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The Five, and it earned the spot — the wire scored it 9 of 10, I chose it.
Best enjoyed by a builder running agents end to end. The move: put it in the loop and watch the second pass.
Filed on THE LOOP DESK, beside 2 more today: “IBM Bob - An AI-Powered Development Partner for Enterprise Modernization”; “Comparison of MCP, RAG, and AI Agents in CX Systems”.
Martin Fowler — 9 appearances in the Times since August 24, 4 of them today.
Pulled from Martin Fowler. The original is worth your click — the byline earned it.
THE CONTEXT DESK today: quiet — nothing on the wire fit it.
Nothing landed here today. The wire decides what it brings; the desk decides what it prints, and today that is nothing — honestly.
THE VERIFY DESK today: 3 stories.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The Five, and it earned the spot — the wire scored it 7 of 10, I chose it.
Best enjoyed by a quality lead, or anyone who signs off. The move: ask what proof would have caught it.
Filed on THE VERIFY DESK, beside 2 more today: “OpenAI will sell you Astra, but not the system that scored 98.6% on ARC-AGI-3”; “AI agent evaluations are part of the product”.
Simon Willison — 20 appearances in the Times since August 21, 2 of them today.
Pulled from Simon Willison. The original is worth your click — the byline earned it.
THE FLEET DESK today: 4 stories.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
Made the wire at 8 of 10. Not the lead, and I'd still not leave it on the floor.
The reader this serves: a leader scaling past one agent. The move: count what it costs before it scales.
Filed on THE FLEET DESK, beside 3 more today: “LLM Text Detection and Autonomous Agent Architecture in AI Development”; “Agentic Engineering at Zalando and Beyond”, and 1 more.
Martin Fowler — 9 appearances in the Times since August 24, 4 of them today.
Martin Fowler has the full story; we hold the door open. Go read the original.
THE WIRE today: 5 stories.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The Five, and it earned the spot — the wire scored it 7 of 10, I chose it.
One for any reader building with agents. The move: share it with whoever will ask about it first.
Front page, beside the rest of today's Five: “Reevaluating Code Review in the Age of AI”; “IBM Bob - An AI-Powered Development Partner for Enterprise Modernization”, and 2 more.
opentrailpaper.com — first appearance in the Times. Found via Hacker News Best.
Pulled from opentrailpaper.com. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The Five, and it earned the spot — the wire scored it 9 of 10, I chose it.
Best enjoyed by a builder running agents end to end. The move: put it in the loop and watch the second pass.
Filed on THE LOOP DESK, beside 2 more today: “IBM Bob - An AI-Powered Development Partner for Enterprise Modernization”; “Comparison of MCP, RAG, and AI Agents in CX Systems”.
Martin Fowler — 9 appearances in the Times since August 24, 4 of them today.
Pulled from Martin Fowler. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The Five, and it earned the spot — the wire scored it 8 of 10, I chose it.
Best enjoyed by a builder running agents end to end. The move: put it in the loop and watch the second pass.
Filed on THE LOOP DESK, beside 2 more today: “Reevaluating Code Review in the Age of AI”; “Comparison of MCP, RAG, and AI Agents in CX Systems”.
bob.ibm.com — first appearance in the Times. Found via Hacker News Best.
Pulled from bob.ibm.com. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The wire scored it 7 of 10 — inside pages, and worth the ink.
Made for a builder running agents end to end, whether they know it yet or not. The move: run it end to end once before believing it.
Filed on THE LOOP DESK, beside 2 more today: “Reevaluating Code Review in the Age of AI”; “IBM Bob - An AI-Powered Development Partner for Enterprise Modernization”.
ByteByteGo — 5 appearances in the Times since August 22, one of them today.
Our page is the summary; ByteByteGo's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The Five, and it earned the spot — the wire scored it 7 of 10, I chose it.
Best enjoyed by a quality lead, or anyone who signs off. The move: ask what proof would have caught it.
Filed on THE VERIFY DESK, beside 2 more today: “OpenAI will sell you Astra, but not the system that scored 98.6% on ARC-AGI-3”; “AI agent evaluations are part of the product”.
Simon Willison — 20 appearances in the Times since August 21, 2 of them today.
Pulled from Simon Willison. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
Inside pages at 5 of 10. The lead had a bigger day; this one had a point.
One for a quality lead, or anyone who signs off. The move: ask what proof would have caught it.
Filed on THE VERIFY DESK, beside 2 more today: “August Newsletter Highlights by Simon Willison”; “AI agent evaluations are part of the product”.
The New Stack — 59 appearances in the Times since August 22, 2 of them today.
Pulled from The New Stack. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The wire scored it 5 of 10 — inside pages, and worth the ink.
This lands hardest with a quality lead, or anyone who signs off. The move: write the test before the fix.
Filed on THE VERIFY DESK, beside 2 more today: “August Newsletter Highlights by Simon Willison”; “OpenAI will sell you Astra, but not the system that scored 98.6% on ARC-AGI-3”.
The New Stack — 59 appearances in the Times since August 22, 2 of them today.
Our page is the summary; The New Stack's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
Made the wire at 8 of 10. Not the lead, and I'd still not leave it on the floor.
The reader this serves: a leader scaling past one agent. The move: count what it costs before it scales.
Filed on THE FLEET DESK, beside 3 more today: “LLM Text Detection and Autonomous Agent Architecture in AI Development”; “Agentic Engineering at Zalando and Beyond”, and 1 more.
Martin Fowler — 9 appearances in the Times since August 24, 4 of them today.
Martin Fowler has the full story; we hold the door open. Go read the original.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
Inside pages at 7 of 10. The lead had a bigger day; this one had a point.
One for a leader scaling past one agent. The move: pilot it on one team before the fleet.
Filed on THE FLEET DESK, beside 3 more today: “Accidental Discovery of Blackboard Systems in Agentic Engineering”; “Agentic Engineering at Zalando and Beyond”, and 1 more.
Martin Fowler — 9 appearances in the Times since August 24, 4 of them today.
Pulled from Martin Fowler. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The wire scored it 7 of 10 — inside pages, and worth the ink.
Made for a leader scaling past one agent, whether they know it yet or not. The move: read it with the team lead in the room.
Filed on THE FLEET DESK, beside 3 more today: “Accidental Discovery of Blackboard Systems in Agentic Engineering”; “LLM Text Detection and Autonomous Agent Architecture in AI Development”, and 1 more.
Martin Fowler — 9 appearances in the Times since August 24, 4 of them today.
Our page is the summary; Martin Fowler's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The wire scored it 6 of 10 — inside pages, and worth the ink.
Made for a leader scaling past one agent, whether they know it yet or not. The move: read it with the team lead in the room.
Filed on THE FLEET DESK, beside 3 more today: “Accidental Discovery of Blackboard Systems in Agentic Engineering”; “LLM Text Detection and Autonomous Agent Architecture in AI Development”, and 1 more.
Simon Willison — 20 appearances in the Times since August 21, 2 of them today.
Our page is the summary; Simon Willison's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The Five, and it earned the spot — the wire scored it 7 of 10, I chose it.
One for any reader building with agents. The move: share it with whoever will ask about it first.
Front page, beside the rest of today's Five: “Reevaluating Code Review in the Age of AI”; “IBM Bob - An AI-Powered Development Partner for Enterprise Modernization”, and 2 more.
opentrailpaper.com — first appearance in the Times. Found via Hacker News Best.
Pulled from opentrailpaper.com. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
Today's Five, front page: the wire scored it 6 of 10; the stamp is mine.
This lands hardest with any reader building with agents. The move: read it before the day fills up.
Front page, beside the rest of today's Five: “Reevaluating Code Review in the Age of AI”; “IBM Bob - An AI-Powered Development Partner for Enterprise Modernization”, and 2 more.
news.gallup.com — first appearance in the Times. Found via Hacker News Best.
Our page is the summary; news.gallup.com's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
Made the wire at 5 of 10. Not the lead, and I'd still not leave it on the floor.
The reader this serves: any reader building with agents. The move: keep it for the next time the question comes up.
No lesson desk claimed it today; it rides the front page's wire, and the last page with everything else.
Anthropic Blog — first appearance in the Times. Found via Hacker News Best.
Anthropic Blog has the full story; we hold the door open. Go read the original.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
The wire scored it 5 of 10 — inside pages, and worth the ink.
This lands hardest with any reader building with agents. The move: read it before the day fills up.
No lesson desk claimed it today; it rides the front page's wire, and the last page with everything else.
torrentfreak.com — first appearance in the Times. Found via Hacker News Best.
Our page is the summary; torrentfreak.com's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 5 edition, and it still holds up.
Made the wire at 5 of 10. Not the lead, and I'd still not leave it on the floor.
Any reader building with agents will get the most from this one. The move: keep it for the next time the question comes up.
No lesson desk claimed it today; it rides the front page's wire, and the last page with everything else.
productrise.app — first appearance in the Times. Found via Hacker News Best.
productrise.app has the full story; we hold the door open. Go read the original.
The library holds nothing on this topic — so far. I'm not done digging.
Martin Fowler: 9 in our pages since August 24. I read them all — emphasis on investigative.
Our files tag it: code review, AI, software quality, pair programming.
The story is at Martin Fowler. I read it to the bottom; you should too.
No story on this desk today, so no notes — I don't write about what didn't happen. Check the front page; the day is there.
No story on this desk today, so no notes — I don't write about what didn't happen. Check the front page; the day is there.
The library holds nothing on this topic — so far. I'm not done digging.
Martin Fowler: 9 in our pages since August 24. I read them all — emphasis on investigative.
Our files tag it: code review, AI, software quality, pair programming.
The story is at Martin Fowler. I read it to the bottom; you should too.
No story on this desk today, so no notes — I don't write about what didn't happen. Check the front page; the day is there.
No paper on the shelf claims this one. Who benefits, and why now? Those are my next two questions.
Simon Willison: 20 in our pages since August 21. I read them all — emphasis on investigative.
Our files tag it: openai, security, claudiauto mode, chatgpt insights.
The story is at Simon Willison. I read it to the bottom; you should too.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Martin Fowler: 9 in our pages since August 24. I read them all — emphasis on investigative.
Our files tag it: agentic engineering, blackboard systems, irops project, ai native sdlc.
Read Martin Fowler's original — they did the legwork, and the detail lives there.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
opentrailpaper.com: first time in our pages. I'll be reading them from here.
Our files tag it: diy bike computer, open source firmware, gps navigation.
The story is at opentrailpaper.com. I read it to the bottom; you should too.
The library holds nothing on this topic — so far. I'm not done digging.
Martin Fowler: 9 in our pages since August 24. I read them all — emphasis on investigative.
Our files tag it: code review, AI, software quality, pair programming.
The story is at Martin Fowler. I read it to the bottom; you should too.
No paper on the shelf claims this one. Who benefits, and why now? Those are my next two questions.
bob.ibm.com: first time in our pages. I'll be reading them from here.
Our files tag it: agile development, legacy modernization, javamodernization, enterprise software.
The story is at bob.ibm.com. I read it to the bottom; you should too.
The library holds nothing on this topic — so far. I'm not done digging.
ByteByteGo: 5 in our pages since August 22. I read them all — emphasis on investigative.
Our files tag it: mcp_protocol, rag_technology, ai_agents, cx_systems.
ByteByteGo filed the full piece. The byline earned the click; go give it.
No paper on the shelf claims this one. Who benefits, and why now? Those are my next two questions.
Simon Willison: 20 in our pages since August 21. I read them all — emphasis on investigative.
Our files tag it: openai, security, claudiauto mode, chatgpt insights.
The story is at Simon Willison. I read it to the bottom; you should too.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
The New Stack: 59 in our pages since August 22. I read them all — emphasis on investigative.
The story is at The New Stack. I read it to the bottom; you should too.
From the Library's paper on “agent swarm failure modes”:
The New Stack: 59 in our pages since August 22. I read them all — emphasis on investigative.
The New Stack filed the full piece. The byline earned the click; go give it.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Martin Fowler: 9 in our pages since August 24. I read them all — emphasis on investigative.
Our files tag it: agentic engineering, blackboard systems, irops project, ai native sdlc.
Read Martin Fowler's original — they did the legwork, and the detail lives there.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
Martin Fowler: 9 in our pages since August 24. I read them all — emphasis on investigative.
Our files tag it: llm generated text, detection tools, autonomous agents, nvidia.
The story is at Martin Fowler. I read it to the bottom; you should too.
No paper on the shelf claims this one. Who benefits, and why now? Those are my next two questions.
Martin Fowler: 9 in our pages since August 24. I read them all — emphasis on investigative.
Our files tag it: zalando, llm assisted code review, security practices, team innovation.
Martin Fowler filed the full piece. The byline earned the click; go give it.
The library holds nothing on this topic — so far. I'm not done digging.
Simon Willison: 20 in our pages since August 21. I read them all — emphasis on investigative.
Simon Willison filed the full piece. The byline earned the click; go give it.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
opentrailpaper.com: first time in our pages. I'll be reading them from here.
Our files tag it: diy bike computer, open source firmware, gps navigation.
The story is at opentrailpaper.com. I read it to the bottom; you should too.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
news.gallup.com: first time in our pages. I'll be reading them from here.
news.gallup.com filed the full piece. The byline earned the click; go give it.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Anthropic Blog: first time in our pages. I'll be reading them from here.
Read Anthropic Blog's original — they did the legwork, and the detail lives there.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
torrentfreak.com: first time in our pages. I'll be reading them from here.
torrentfreak.com filed the full piece. The byline earned the click; go give it.
From the Library's paper on “the price of a human check”:
productrise.app: first time in our pages. I'll be reading them from here.
Read productrise.app's original — they did the legwork, and the detail lives there.