Andrew Stellman 👾
@andrewstellman.bsky.social
Author, developer, team lead, musician.
Author of O'Reilly books including Head First C#, Learning Agile, and Head First PMP.
Solving complexity with simplicity.
Author of O'Reilly books including Head First C#, Learning Agile, and Head First PMP.
Solving complexity with simplicity.
You know what's funny? Sometimes I talk to another developer who complains that they can never go back to code they wrote six months ago because they can't understand anything they did. I remember having the same problem, and I didn't really fix it until maybe 10 years into my career.
November 21, 2025 at 3:02 PM
You know what's funny? Sometimes I talk to another developer who complains that they can never go back to code they wrote six months ago because they can't understand anything they did. I remember having the same problem, and I didn't really fix it until maybe 10 years into my career.
It's not easy, but you can get Copilot to talk like a pirate.
November 14, 2025 at 3:04 PM
It's not easy, but you can get Copilot to talk like a pirate.
🚀 𝐓𝐡𝐞 𝐒𝐞𝐧𝐬-𝐀𝐈 𝐅𝐫𝐚𝐦𝐞𝐰𝐨𝐫𝐤 𝐬𝐭𝐚𝐫𝐭𝐞𝐝 𝐚𝐬 𝐨𝐧𝐞 𝐢𝐝𝐞𝐚. 𝐍𝐨𝐰 𝐢𝐭’𝐬 𝐚 𝐜𝐨𝐦𝐩𝐥𝐞𝐭𝐞 𝐫𝐨𝐚𝐝𝐦𝐚𝐩 𝐟𝐨𝐫 𝐜𝐨𝐝𝐢𝐧𝐠 𝐰𝐢𝐭𝐡 𝐀𝐈. 🚀
I’m really excited to share that my full @oreilly.bsky.social Radar 𝐒𝐞𝐧𝐬-𝐀𝐈 𝐅𝐫𝐚𝐦𝐞𝐰𝐨𝐫𝐤 series is now complete, along with the new O’Reilly report, 𝑪𝒓𝒊𝒕𝒊𝒄𝒂𝒍 𝑻𝒉𝒊𝒏𝒌𝒊𝒏𝒈 𝑯𝒂𝒃𝒊𝒕𝒔 𝒇𝒐𝒓 𝑪𝒐𝒅𝒊𝒏𝒈 𝒘𝒊𝒕𝒉 𝑨𝑰.
October 28, 2025 at 1:23 PM
🚀 𝐓𝐡𝐞 𝐒𝐞𝐧𝐬-𝐀𝐈 𝐅𝐫𝐚𝐦𝐞𝐰𝐨𝐫𝐤 𝐬𝐭𝐚𝐫𝐭𝐞𝐝 𝐚𝐬 𝐨𝐧𝐞 𝐢𝐝𝐞𝐚. 𝐍𝐨𝐰 𝐢𝐭’𝐬 𝐚 𝐜𝐨𝐦𝐩𝐥𝐞𝐭𝐞 𝐫𝐨𝐚𝐝𝐦𝐚𝐩 𝐟𝐨𝐫 𝐜𝐨𝐝𝐢𝐧𝐠 𝐰𝐢𝐭𝐡 𝐀𝐈. 🚀
I’m really excited to share that my full @oreilly.bsky.social Radar 𝐒𝐞𝐧𝐬-𝐀𝐈 𝐅𝐫𝐚𝐦𝐞𝐰𝐨𝐫𝐤 series is now complete, along with the new O’Reilly report, 𝑪𝒓𝒊𝒕𝒊𝒄𝒂𝒍 𝑻𝒉𝒊𝒏𝒌𝒊𝒏𝒈 𝑯𝒂𝒃𝒊𝒕𝒔 𝒇𝒐𝒓 𝑪𝒐𝒅𝒊𝒏𝒈 𝒘𝒊𝒕𝒉 𝑨𝑰.
🚀 𝐄𝐱𝐜𝐢𝐭𝐞𝐝 𝐭𝐨 𝐚𝐧𝐧𝐨𝐮𝐧𝐜𝐞 𝐭𝐡𝐚𝐭 𝐦𝐲 𝐧𝐞𝐰 @oreilly.bsky.social 𝐫𝐞𝐩𝐨𝐫𝐭 𝐢𝐬 𝐧𝐨𝐰 𝐥𝐢𝐯𝐞! 🚀
I’m really excited about this one. It’s the culmination of months of research, writing, and hands-on testing with real developers.
I’m really excited about this one. It’s the culmination of months of research, writing, and hands-on testing with real developers.
October 27, 2025 at 2:31 PM
🚀 𝐄𝐱𝐜𝐢𝐭𝐞𝐝 𝐭𝐨 𝐚𝐧𝐧𝐨𝐮𝐧𝐜𝐞 𝐭𝐡𝐚𝐭 𝐦𝐲 𝐧𝐞𝐰 @oreilly.bsky.social 𝐫𝐞𝐩𝐨𝐫𝐭 𝐢𝐬 𝐧𝐨𝐰 𝐥𝐢𝐯𝐞! 🚀
I’m really excited about this one. It’s the culmination of months of research, writing, and hands-on testing with real developers.
I’m really excited about this one. It’s the culmination of months of research, writing, and hands-on testing with real developers.
🚀 𝐌𝐲 𝐧𝐞𝐰 𝐎’𝐑𝐞𝐢𝐥𝐥𝐲 𝐑𝐚𝐝𝐚𝐫 𝐚𝐫𝐭𝐢𝐜𝐥𝐞 𝐣𝐮𝐬𝐭 𝐝𝐫𝐨𝐩𝐩𝐞𝐝! 🚀
This one wraps up the Sens-AI series — and it’s about something I’ve been seeing more and more in the real world: how AI is reshaping what it means to be a developer.
This one wraps up the Sens-AI series — and it’s about something I’ve been seeing more and more in the real world: how AI is reshaping what it means to be a developer.
October 24, 2025 at 1:28 PM
🚀 𝐌𝐲 𝐧𝐞𝐰 𝐎’𝐑𝐞𝐢𝐥𝐥𝐲 𝐑𝐚𝐝𝐚𝐫 𝐚𝐫𝐭𝐢𝐜𝐥𝐞 𝐣𝐮𝐬𝐭 𝐝𝐫𝐨𝐩𝐩𝐞𝐝! 🚀
This one wraps up the Sens-AI series — and it’s about something I’ve been seeing more and more in the real world: how AI is reshaping what it means to be a developer.
This one wraps up the Sens-AI series — and it’s about something I’ve been seeing more and more in the real world: how AI is reshaping what it means to be a developer.
Reposted by Andrew Stellman 👾
"The developers who succeed in an AI-enabled world won’t always be the ones who know the most. They’ll be the ones who can see the bigger picture, integrate across systems, and use AI as a powerful tool while maintaining the critical thinking." @andrewstellman.bsky.social bit.ly/4qpsROx #Radar #AI
AI Is Reshaping Developer Career Paths
From Specialists to Generalists
bit.ly
October 23, 2025 at 9:54 PM
"The developers who succeed in an AI-enabled world won’t always be the ones who know the most. They’ll be the ones who can see the bigger picture, integrate across systems, and use AI as a powerful tool while maintaining the critical thinking." @andrewstellman.bsky.social bit.ly/4qpsROx #Radar #AI
Reposted by Andrew Stellman 👾
"The next generation of developers will never know coding without AI. Our job is to make sure they build lasting engineering habits alongside these tools—so AI strengthens their craft rather than hollowing it out." Check out #Radar article by @andrewstellman.bsky.social: bit.ly/3IZFy1Y #AICoding
From Habits to Tools
The Future of AI-Assisted Development
bit.ly
October 21, 2025 at 6:02 PM
"The next generation of developers will never know coding without AI. Our job is to make sure they build lasting engineering habits alongside these tools—so AI strengthens their craft rather than hollowing it out." Check out #Radar article by @andrewstellman.bsky.social: bit.ly/3IZFy1Y #AICoding
🚀 𝐓𝐡𝐞 𝐟𝐮𝐭𝐮𝐫𝐞 𝐨𝐟 𝐀𝐈 𝐝𝐞𝐯𝐞𝐥𝐨𝐩𝐦𝐞𝐧𝐭 𝐢𝐬𝐧’𝐭 𝐚𝐛𝐨𝐮𝐭 𝐭𝐨𝐨𝐥𝐬. 𝐈𝐭’𝐬 𝐚𝐛𝐨𝐮𝐭 𝐡𝐚𝐛𝐢𝐭𝐬. 🚀
When teams talk about “AI adoption,” they usually mean installing Copilot or tracking metrics. That’s only the surface layer.
When teams talk about “AI adoption,” they usually mean installing Copilot or tracking metrics. That’s only the surface layer.
October 20, 2025 at 1:15 PM
🚀 𝐓𝐡𝐞 𝐟𝐮𝐭𝐮𝐫𝐞 𝐨𝐟 𝐀𝐈 𝐝𝐞𝐯𝐞𝐥𝐨𝐩𝐦𝐞𝐧𝐭 𝐢𝐬𝐧’𝐭 𝐚𝐛𝐨𝐮𝐭 𝐭𝐨𝐨𝐥𝐬. 𝐈𝐭’𝐬 𝐚𝐛𝐨𝐮𝐭 𝐡𝐚𝐛𝐢𝐭𝐬. 🚀
When teams talk about “AI adoption,” they usually mean installing Copilot or tracking metrics. That’s only the surface layer.
When teams talk about “AI adoption,” they usually mean installing Copilot or tracking metrics. That’s only the surface layer.
🚀 𝐀𝐈 𝐰𝐨𝐧’𝐭 𝐫𝐞𝐩𝐥𝐚𝐜𝐞 𝐝𝐞𝐯𝐞𝐥𝐨𝐩𝐞𝐫𝐬. 𝐈𝐭 𝐰𝐢𝐥𝐥 𝐜𝐡𝐚𝐧𝐠𝐞 𝐰𝐡𝐢𝐜𝐡 𝐡𝐚𝐛𝐢𝐭𝐬 𝐦𝐚𝐭𝐭𝐞𝐫. 🚀
AI tools help us move faster, but sometimes that speed means we stop noticing why our code works. The real danger isn’t just writing a weak prompt. It’s drifting so far from the code that we forget how it fits together.
AI tools help us move faster, but sometimes that speed means we stop noticing why our code works. The real danger isn’t just writing a weak prompt. It’s drifting so far from the code that we forget how it fits together.
October 17, 2025 at 5:52 PM
🚀 𝐀𝐈 𝐰𝐨𝐧’𝐭 𝐫𝐞𝐩𝐥𝐚𝐜𝐞 𝐝𝐞𝐯𝐞𝐥𝐨𝐩𝐞𝐫𝐬. 𝐈𝐭 𝐰𝐢𝐥𝐥 𝐜𝐡𝐚𝐧𝐠𝐞 𝐰𝐡𝐢𝐜𝐡 𝐡𝐚𝐛𝐢𝐭𝐬 𝐦𝐚𝐭𝐭𝐞𝐫. 🚀
AI tools help us move faster, but sometimes that speed means we stop noticing why our code works. The real danger isn’t just writing a weak prompt. It’s drifting so far from the code that we forget how it fits together.
AI tools help us move faster, but sometimes that speed means we stop noticing why our code works. The real danger isn’t just writing a weak prompt. It’s drifting so far from the code that we forget how it fits together.
🚀 𝐌𝐲 𝐧𝐞𝐰 @oreilly.bsky.social 𝐑𝐚𝐝𝐚𝐫 𝐩𝐢𝐞𝐜𝐞 𝐣𝐮𝐬𝐭 𝐝𝐫𝐨𝐩𝐩𝐞𝐝! 🚀
AI-assisted coding isn’t new anymore—most developers use Copilot or ChatGPT every day. But what we haven’t figured out yet is how to keep our engineering skills sharp while we do it.
AI-assisted coding isn’t new anymore—most developers use Copilot or ChatGPT every day. But what we haven’t figured out yet is how to keep our engineering skills sharp while we do it.
October 15, 2025 at 3:10 PM
🚀 𝐌𝐲 𝐧𝐞𝐰 @oreilly.bsky.social 𝐑𝐚𝐝𝐚𝐫 𝐩𝐢𝐞𝐜𝐞 𝐣𝐮𝐬𝐭 𝐝𝐫𝐨𝐩𝐩𝐞𝐝! 🚀
AI-assisted coding isn’t new anymore—most developers use Copilot or ChatGPT every day. But what we haven’t figured out yet is how to keep our engineering skills sharp while we do it.
AI-assisted coding isn’t new anymore—most developers use Copilot or ChatGPT every day. But what we haven’t figured out yet is how to keep our engineering skills sharp while we do it.
Reposted by Andrew Stellman 👾
"Teaching developers to work effectively with AI means building habits that keep critical thinking active while leveraging AI’s speed. But teaching these habits isn’t straightforward." Check out new #Radar article by @andrewstellman.bsky.social: bit.ly/3KJJ8h9 #AI
The AI Teaching Toolkit: Practical Guidance for Teams
Teaching developers to work effectively with AI means building habits that keep critical thinking active while leveraging AI’s speed.But teaching these
bit.ly
October 10, 2025 at 4:48 PM
"Teaching developers to work effectively with AI means building habits that keep critical thinking active while leveraging AI’s speed. But teaching these habits isn’t straightforward." Check out new #Radar article by @andrewstellman.bsky.social: bit.ly/3KJJ8h9 #AI
Reposted by Andrew Stellman 👾
The cognitive shortcut paradox presents a fundamental challenge for how we teach and learn #programming in the #AI era. The traditional path of building skills through struggle and iteration hasn’t become obsolete; it’s become more critical. @andrewstellman.bsky.social: bit.ly/4nyzhcB #Radar
The Cognitive Shortcut Paradox
This article is part of a series on the Sens-AI Framework—practical habits for learning and coding with AI.AI gives novice developers the ability to skip
bit.ly
October 2, 2025 at 7:31 PM
The cognitive shortcut paradox presents a fundamental challenge for how we teach and learn #programming in the #AI era. The traditional path of building skills through struggle and iteration hasn’t become obsolete; it’s become more critical. @andrewstellman.bsky.social: bit.ly/4nyzhcB #Radar
🚀 𝗔𝗜 𝘄𝗼𝗻’𝘁 𝗸𝗶𝗹𝗹 𝗰𝗼𝗱𝗶𝗻𝗴—𝗵𝗲𝗿𝗲’𝘀 𝘄𝗵𝘆 🚀
I got a thoughtful reply on one of my posts: we’re in a transition phase where LLMs cover 80% of the work, and once the last 20% is solved, we’ll just be writing apps in natural language instead of code.
It’s a smart take—and it’s also something I hear a lot.
I got a thoughtful reply on one of my posts: we’re in a transition phase where LLMs cover 80% of the work, and once the last 20% is solved, we’ll just be writing apps in natural language instead of code.
It’s a smart take—and it’s also something I hear a lot.
October 2, 2025 at 4:40 PM
🚀 𝗔𝗜 𝘄𝗼𝗻’𝘁 𝗸𝗶𝗹𝗹 𝗰𝗼𝗱𝗶𝗻𝗴—𝗵𝗲𝗿𝗲’𝘀 𝘄𝗵𝘆 🚀
I got a thoughtful reply on one of my posts: we’re in a transition phase where LLMs cover 80% of the work, and once the last 20% is solved, we’ll just be writing apps in natural language instead of code.
It’s a smart take—and it’s also something I hear a lot.
I got a thoughtful reply on one of my posts: we’re in a transition phase where LLMs cover 80% of the work, and once the last 20% is solved, we’ll just be writing apps in natural language instead of code.
It’s a smart take—and it’s also something I hear a lot.
🚀 𝗧𝗵𝗲 𝗖𝗼𝗴𝗻𝗶𝘁𝗶𝘃𝗲 𝗦𝗵𝗼𝗿𝘁𝗰𝘂𝘁 𝗣𝗮𝗿𝗮𝗱𝗼𝘅: 𝗪𝗵𝗲𝗻 𝗔𝗜 𝗵𝗲𝗹𝗽𝘀 𝘀𝗲𝗻𝗶𝗼𝗿𝘀 𝗯𝘂𝘁 𝗵𝘂𝗿𝘁𝘀 𝗷𝘂𝗻𝗶𝗼𝗿𝘀 🚀
Evidence is emerging that AI chatbots boost productivity for experienced developers—but have little measurable impact on skill growth for beginners.
That’s the heart of what I call the 𝗰𝗼𝗴𝗻𝗶𝘁𝗶𝘃𝗲 𝘀𝗵𝗼𝗿𝘁𝗰𝘂𝘁 𝗽𝗮𝗿𝗮𝗱𝗼𝘅.
Evidence is emerging that AI chatbots boost productivity for experienced developers—but have little measurable impact on skill growth for beginners.
That’s the heart of what I call the 𝗰𝗼𝗴𝗻𝗶𝘁𝗶𝘃𝗲 𝘀𝗵𝗼𝗿𝘁𝗰𝘂𝘁 𝗽𝗮𝗿𝗮𝗱𝗼𝘅.
The Cognitive Shortcut Paradox
This article is part of a series on the Sens-AI Framework—practical habits for learning and coding with AI.AI gives novice developers the ability to skip
www.oreilly.com
October 2, 2025 at 1:52 PM
🚀 𝗧𝗵𝗲 𝗖𝗼𝗴𝗻𝗶𝘁𝗶𝘃𝗲 𝗦𝗵𝗼𝗿𝘁𝗰𝘂𝘁 𝗣𝗮𝗿𝗮𝗱𝗼𝘅: 𝗪𝗵𝗲𝗻 𝗔𝗜 𝗵𝗲𝗹𝗽𝘀 𝘀𝗲𝗻𝗶𝗼𝗿𝘀 𝗯𝘂𝘁 𝗵𝘂𝗿𝘁𝘀 𝗷𝘂𝗻𝗶𝗼𝗿𝘀 🚀
Evidence is emerging that AI chatbots boost productivity for experienced developers—but have little measurable impact on skill growth for beginners.
That’s the heart of what I call the 𝗰𝗼𝗴𝗻𝗶𝘁𝗶𝘃𝗲 𝘀𝗵𝗼𝗿𝘁𝗰𝘂𝘁 𝗽𝗮𝗿𝗮𝗱𝗼𝘅.
Evidence is emerging that AI chatbots boost productivity for experienced developers—but have little measurable impact on skill growth for beginners.
That’s the heart of what I call the 𝗰𝗼𝗴𝗻𝗶𝘁𝗶𝘃𝗲 𝘀𝗵𝗼𝗿𝘁𝗰𝘂𝘁 𝗽𝗮𝗿𝗮𝗱𝗼𝘅.
🚀 𝗧𝗵𝗲 𝗛𝗶𝗱𝗱𝗲𝗻 𝗰𝗼𝘀𝘁 𝗼𝗳 𝗔𝗜 𝗰𝗼𝗱𝗶𝗻𝗴: 𝗧𝗵𝗲 𝗖𝗼𝗴𝗻𝗶𝘁𝗶𝘃𝗲 𝗦𝗵𝗼𝗿𝘁𝗰𝘂𝘁 𝗣𝗮𝗿𝗮𝗱𝗼𝘅 🚀
I’m really excited to share my latest Radar piece: “The Cognitive Shortcut Paradox.”
AI gives developers the ability to skip the slow, messy parts of coding. That feels great…
I’m really excited to share my latest Radar piece: “The Cognitive Shortcut Paradox.”
AI gives developers the ability to skip the slow, messy parts of coding. That feels great…
October 1, 2025 at 1:31 PM
🚀 𝗧𝗵𝗲 𝗛𝗶𝗱𝗱𝗲𝗻 𝗰𝗼𝘀𝘁 𝗼𝗳 𝗔𝗜 𝗰𝗼𝗱𝗶𝗻𝗴: 𝗧𝗵𝗲 𝗖𝗼𝗴𝗻𝗶𝘁𝗶𝘃𝗲 𝗦𝗵𝗼𝗿𝘁𝗰𝘂𝘁 𝗣𝗮𝗿𝗮𝗱𝗼𝘅 🚀
I’m really excited to share my latest Radar piece: “The Cognitive Shortcut Paradox.”
AI gives developers the ability to skip the slow, messy parts of coding. That feels great…
I’m really excited to share my latest Radar piece: “The Cognitive Shortcut Paradox.”
AI gives developers the ability to skip the slow, messy parts of coding. That feels great…
🚀 𝗛𝗼𝘄 𝘁𝗼 𝘂𝘀𝗲 𝗔𝗜 𝘁𝗼 𝗰𝗮𝘁𝗰𝗵 𝗶𝘁𝘀 𝗼𝘄𝗻 𝗺𝗶𝘀𝘁𝗮𝗸𝗲𝘀 🚀
Here’s a trick: after Copilot or ChatGPT generates code, ask it to review that same code for problems. Because the model shifts context, it often surfaces issues it “missed” the first time: contradictory feedback, nitpicky warnings, or edge cases.
Here’s a trick: after Copilot or ChatGPT generates code, ask it to review that same code for problems. Because the model shifts context, it often surfaces issues it “missed” the first time: contradictory feedback, nitpicky warnings, or edge cases.
September 29, 2025 at 1:34 PM
🚀 𝗛𝗼𝘄 𝘁𝗼 𝘂𝘀𝗲 𝗔𝗜 𝘁𝗼 𝗰𝗮𝘁𝗰𝗵 𝗶𝘁𝘀 𝗼𝘄𝗻 𝗺𝗶𝘀𝘁𝗮𝗸𝗲𝘀 🚀
Here’s a trick: after Copilot or ChatGPT generates code, ask it to review that same code for problems. Because the model shifts context, it often surfaces issues it “missed” the first time: contradictory feedback, nitpicky warnings, or edge cases.
Here’s a trick: after Copilot or ChatGPT generates code, ask it to review that same code for problems. Because the model shifts context, it often surfaces issues it “missed” the first time: contradictory feedback, nitpicky warnings, or edge cases.
🚀 𝗧𝗵𝗲 𝘀𝘂𝗯𝘁𝗹𝗲 𝘀𝗶𝗴𝗻𝘀 𝘆𝗼𝘂𝗿 𝗔𝗜-𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝗱 𝗰𝗼𝗱𝗲 𝗶𝘀 𝗶𝗻 𝘁𝗿𝗼𝘂𝗯𝗹𝗲 🚀
How do you know when to stop vibe coding and start verifying? Watch for the signals:
🔄 𝗥𝗲𝗵𝗮𝘀𝗵 𝗹𝗼𝗼𝗽𝘀: prompting slight variations over and over without progress
💥 𝗦𝗵𝗼𝘁𝗴𝘂𝗻 𝘀𝘂𝗿𝗴𝗲𝗿𝘆: one small change triggers cascading edits everywhere
How do you know when to stop vibe coding and start verifying? Watch for the signals:
🔄 𝗥𝗲𝗵𝗮𝘀𝗵 𝗹𝗼𝗼𝗽𝘀: prompting slight variations over and over without progress
💥 𝗦𝗵𝗼𝘁𝗴𝘂𝗻 𝘀𝘂𝗿𝗴𝗲𝗿𝘆: one small change triggers cascading edits everywhere
September 26, 2025 at 1:58 PM
🚀 𝗧𝗵𝗲 𝘀𝘂𝗯𝘁𝗹𝗲 𝘀𝗶𝗴𝗻𝘀 𝘆𝗼𝘂𝗿 𝗔𝗜-𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝗱 𝗰𝗼𝗱𝗲 𝗶𝘀 𝗶𝗻 𝘁𝗿𝗼𝘂𝗯𝗹𝗲 🚀
How do you know when to stop vibe coding and start verifying? Watch for the signals:
🔄 𝗥𝗲𝗵𝗮𝘀𝗵 𝗹𝗼𝗼𝗽𝘀: prompting slight variations over and over without progress
💥 𝗦𝗵𝗼𝘁𝗴𝘂𝗻 𝘀𝘂𝗿𝗴𝗲𝗿𝘆: one small change triggers cascading edits everywhere
How do you know when to stop vibe coding and start verifying? Watch for the signals:
🔄 𝗥𝗲𝗵𝗮𝘀𝗵 𝗹𝗼𝗼𝗽𝘀: prompting slight variations over and over without progress
💥 𝗦𝗵𝗼𝘁𝗴𝘂𝗻 𝘀𝘂𝗿𝗴𝗲𝗿𝘆: one small change triggers cascading edits everywhere
Reposted by Andrew Stellman 👾
"Watch for signs of trouble: lots of mocking, complex setup, too many dependencies—especially needing to modify other parts of the code. When you see those signs, stop vibe coding and read the code." Check out new #Radar article by @andrewstellman.bsky.social: bit.ly/4nQMeOx #AI #VibeCoding
Trust but Verify
Learning to Catch What AI Misses
bit.ly
September 25, 2025 at 7:47 PM
"Watch for signs of trouble: lots of mocking, complex setup, too many dependencies—especially needing to modify other parts of the code. When you see those signs, stop vibe coding and read the code." Check out new #Radar article by @andrewstellman.bsky.social: bit.ly/4nQMeOx #AI #VibeCoding
🚀 𝗧𝗵𝗲 𝗔𝗜 𝗿𝘂𝗹𝗲 𝗲𝘃𝗲𝗿𝘆 𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿 𝗻𝗲𝗲𝗱𝘀: 𝗧𝗿𝘂𝘀𝘁 𝗯𝘂𝘁 𝘃𝗲𝗿𝗶𝗳𝘆 🚀
AI-generated code looks right a lot of the time—but it’s not guaranteed. It’s stitching patterns together, not reasoning about your architecture or long-term design.
That’s why I argue the mindset has to be 𝘁𝗿𝘂𝘀𝘁 𝗯𝘂𝘁 𝘃𝗲𝗿𝗶𝗳𝘆.
AI-generated code looks right a lot of the time—but it’s not guaranteed. It’s stitching patterns together, not reasoning about your architecture or long-term design.
That’s why I argue the mindset has to be 𝘁𝗿𝘂𝘀𝘁 𝗯𝘂𝘁 𝘃𝗲𝗿𝗶𝗳𝘆.
September 25, 2025 at 1:32 PM
🚀 𝗧𝗵𝗲 𝗔𝗜 𝗿𝘂𝗹𝗲 𝗲𝘃𝗲𝗿𝘆 𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿 𝗻𝗲𝗲𝗱𝘀: 𝗧𝗿𝘂𝘀𝘁 𝗯𝘂𝘁 𝘃𝗲𝗿𝗶𝗳𝘆 🚀
AI-generated code looks right a lot of the time—but it’s not guaranteed. It’s stitching patterns together, not reasoning about your architecture or long-term design.
That’s why I argue the mindset has to be 𝘁𝗿𝘂𝘀𝘁 𝗯𝘂𝘁 𝘃𝗲𝗿𝗶𝗳𝘆.
AI-generated code looks right a lot of the time—but it’s not guaranteed. It’s stitching patterns together, not reasoning about your architecture or long-term design.
That’s why I argue the mindset has to be 𝘁𝗿𝘂𝘀𝘁 𝗯𝘂𝘁 𝘃𝗲𝗿𝗶𝗳𝘆.
🚀 𝗘𝘅𝗰𝗶𝘁𝗲𝗱 𝘁𝗼 𝘀𝗵𝗮𝗿𝗲: 𝗺𝘆 𝗻𝗲𝘄 @oreilly.bsky.social 𝗥𝗮𝗱𝗮𝗿 𝗮𝗿𝘁𝗶𝗰𝗹𝗲 𝗷𝘂𝘀𝘁 𝗱𝗿𝗼𝗽𝗽𝗲𝗱! 🚀
I’m really excited about this one. It’s called “Trust but Verify” and it digs into how we should be using AI coding tools.
AI can speed up development in amazing ways, but that doesn’t mean you can switch off your brain.
I’m really excited about this one. It’s called “Trust but Verify” and it digs into how we should be using AI coding tools.
AI can speed up development in amazing ways, but that doesn’t mean you can switch off your brain.
September 24, 2025 at 4:31 PM
🚀 𝗘𝘅𝗰𝗶𝘁𝗲𝗱 𝘁𝗼 𝘀𝗵𝗮𝗿𝗲: 𝗺𝘆 𝗻𝗲𝘄 @oreilly.bsky.social 𝗥𝗮𝗱𝗮𝗿 𝗮𝗿𝘁𝗶𝗰𝗹𝗲 𝗷𝘂𝘀𝘁 𝗱𝗿𝗼𝗽𝗽𝗲𝗱! 🚀
I’m really excited about this one. It’s called “Trust but Verify” and it digs into how we should be using AI coding tools.
AI can speed up development in amazing ways, but that doesn’t mean you can switch off your brain.
I’m really excited about this one. It’s called “Trust but Verify” and it digs into how we should be using AI coding tools.
AI can speed up development in amazing ways, but that doesn’t mean you can switch off your brain.
🚀 𝐓𝐡𝐞 𝐀𝐈 𝐩𝐢𝐭𝐟𝐚𝐥𝐥 𝐧𝐨 𝐨𝐧𝐞 𝐭𝐚𝐥𝐤𝐬 𝐚𝐛𝐨𝐮𝐭… 🚀
Here’s something subtle but dangerous: 𝐜𝐨𝐧𝐭𝐞𝐱𝐭 𝐝𝐫𝐢𝐟𝐭. With humans, misunderstandings show up in meetings. With AI, the answers keep sounding confident until suddenly it suggests a fix that makes no sense. 🧵
Here’s something subtle but dangerous: 𝐜𝐨𝐧𝐭𝐞𝐱𝐭 𝐝𝐫𝐢𝐟𝐭. With humans, misunderstandings show up in meetings. With AI, the answers keep sounding confident until suddenly it suggests a fix that makes no sense. 🧵
September 24, 2025 at 2:17 PM
🚀 𝐓𝐡𝐞 𝐀𝐈 𝐩𝐢𝐭𝐟𝐚𝐥𝐥 𝐧𝐨 𝐨𝐧𝐞 𝐭𝐚𝐥𝐤𝐬 𝐚𝐛𝐨𝐮𝐭… 🚀
Here’s something subtle but dangerous: 𝐜𝐨𝐧𝐭𝐞𝐱𝐭 𝐝𝐫𝐢𝐟𝐭. With humans, misunderstandings show up in meetings. With AI, the answers keep sounding confident until suddenly it suggests a fix that makes no sense. 🧵
Here’s something subtle but dangerous: 𝐜𝐨𝐧𝐭𝐞𝐱𝐭 𝐝𝐫𝐢𝐟𝐭. With humans, misunderstandings show up in meetings. With AI, the answers keep sounding confident until suddenly it suggests a fix that makes no sense. 🧵
🚀 𝐀𝐫𝐞 𝐩𝐫𝐨𝐦𝐩𝐭 𝐥𝐢𝐛𝐫𝐚𝐫𝐢𝐞𝐬 𝐭𝐡𝐞 𝐧𝐞𝐰 𝐭𝐞𝐦𝐩𝐥𝐚𝐭𝐞 𝐭𝐫𝐚𝐩? 🚀
In the 1990s, companies built massive templates and forms for requirements documents, hoping the right format would guarantee the right system. It didn’t. That didn’t work, and it often made things worse… 🧵
In the 1990s, companies built massive templates and forms for requirements documents, hoping the right format would guarantee the right system. It didn’t. That didn’t work, and it often made things worse… 🧵
September 23, 2025 at 1:57 PM
🚀 𝐀𝐫𝐞 𝐩𝐫𝐨𝐦𝐩𝐭 𝐥𝐢𝐛𝐫𝐚𝐫𝐢𝐞𝐬 𝐭𝐡𝐞 𝐧𝐞𝐰 𝐭𝐞𝐦𝐩𝐥𝐚𝐭𝐞 𝐭𝐫𝐚𝐩? 🚀
In the 1990s, companies built massive templates and forms for requirements documents, hoping the right format would guarantee the right system. It didn’t. That didn’t work, and it often made things worse… 🧵
In the 1990s, companies built massive templates and forms for requirements documents, hoping the right format would guarantee the right system. It didn’t. That didn’t work, and it often made things worse… 🧵
🚀 𝐏𝐫𝐨𝐦𝐩𝐭 𝐞𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠 𝐢𝐬𝐧’𝐭 𝐧𝐞𝐰—𝐰𝐞 𝐣𝐮𝐬𝐭 𝐜𝐡𝐚𝐧𝐠𝐞𝐝 𝐭𝐡𝐞 𝐧𝐚𝐦𝐞 🚀
In the late 1960s, the NATO Software Engineering Conference kicked off what became known as the “software crisis.” The problem wasn’t a lack of technical skill… 🧵
In the late 1960s, the NATO Software Engineering Conference kicked off what became known as the “software crisis.” The problem wasn’t a lack of technical skill… 🧵
September 22, 2025 at 1:35 PM
🚀 𝐏𝐫𝐨𝐦𝐩𝐭 𝐞𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠 𝐢𝐬𝐧’𝐭 𝐧𝐞𝐰—𝐰𝐞 𝐣𝐮𝐬𝐭 𝐜𝐡𝐚𝐧𝐠𝐞𝐝 𝐭𝐡𝐞 𝐧𝐚𝐦𝐞 🚀
In the late 1960s, the NATO Software Engineering Conference kicked off what became known as the “software crisis.” The problem wasn’t a lack of technical skill… 🧵
In the late 1960s, the NATO Software Engineering Conference kicked off what became known as the “software crisis.” The problem wasn’t a lack of technical skill… 🧵
🚀 𝐀𝐈 𝐦𝐚𝐝𝐞 𝐦𝐞 𝐟𝐞𝐞𝐥 𝐥𝐢𝐤𝐞 𝐈 𝐤𝐧𝐨𝐰 𝐦𝐲 𝐜𝐨𝐝𝐞 𝐛𝐞𝐭𝐭𝐞𝐫… 𝐛𝐮𝐭 𝐢𝐬 𝐢𝐭 𝐫𝐞𝐚𝐥? 🚀
This surprised me. I’ve always cared a lot about architecture, separation of concerns, and keeping classes decoupled. Normally that takes a ton of focus, because it’s so easy to get pulled down into the weeds of the implementation . 🧵
This surprised me. I’ve always cared a lot about architecture, separation of concerns, and keeping classes decoupled. Normally that takes a ton of focus, because it’s so easy to get pulled down into the weeds of the implementation . 🧵
Building AI-Resistant Technical Debt
When Speed Creates Long-Term Pain
www.oreilly.com
September 18, 2025 at 2:09 PM
🚀 𝐀𝐈 𝐦𝐚𝐝𝐞 𝐦𝐞 𝐟𝐞𝐞𝐥 𝐥𝐢𝐤𝐞 𝐈 𝐤𝐧𝐨𝐰 𝐦𝐲 𝐜𝐨𝐝𝐞 𝐛𝐞𝐭𝐭𝐞𝐫… 𝐛𝐮𝐭 𝐢𝐬 𝐢𝐭 𝐫𝐞𝐚𝐥? 🚀
This surprised me. I’ve always cared a lot about architecture, separation of concerns, and keeping classes decoupled. Normally that takes a ton of focus, because it’s so easy to get pulled down into the weeds of the implementation . 🧵
This surprised me. I’ve always cared a lot about architecture, separation of concerns, and keeping classes decoupled. Normally that takes a ton of focus, because it’s so easy to get pulled down into the weeds of the implementation . 🧵
Reposted by Andrew Stellman 👾
"Talking about prompt engineering today is really just continuing a much older conversation about how developers spell out what they need built, under what conditions, with what assumptions, and how to communicate that to the team." New #Radar article by @andrewstellman.bsky.social: bit.ly/4nzKfxQ
Prompt Engineering Is Requirements Engineering
We’ve Been Here Before
bit.ly
September 17, 2025 at 6:03 PM
"Talking about prompt engineering today is really just continuing a much older conversation about how developers spell out what they need built, under what conditions, with what assumptions, and how to communicate that to the team." New #Radar article by @andrewstellman.bsky.social: bit.ly/4nzKfxQ