✕ Clear all filters
32 articles
▶ Videos →

📰 Dev.to · Alex @ Vibe Agent Making

32 articles · Updated every 3 hours · View all reads

All Articles 131,978Blog Posts 136,781Tech Tutorials 34,209Research Papers 25,925News 18,714 ⚡ AI Lessons
The Answer Key Was in the Training Data
Dev.to · Alex @ Vibe Agent Making 3d ago
The Answer Key Was in the Training Data
One axiom unifies benchmark contamination and agent self-grading: a score reflects capability only to...
Why We Hold Every Failed Verify Now: The Fail-Open Gate That Shipped a Broken Build
Dev.to · Alex @ Vibe Agent Making 4d ago
Why We Hold Every Failed Verify Now: The Fail-Open Gate That Shipped a Broken Build
A green checkmark that meant "I did not look" shipped a broken build. The fix was not more tests but...
Citibank's $900 Million Mistake: Six Eyes on an Approval Screen That Never Showed the Amount
Dev.to · Alex @ Vibe Agent Making 5d ago
Citibank's $900 Million Mistake: Six Eyes on an Approval Screen That Never Showed the Amount
Citibank wired $900M by mistake through a six-eyes approval screen that never showed the amount. The...
21% of IT Leaders Say They Can't See Their Own AI Agents. I Fed 11 of My Own Checks Empty Input, and 5 Passed in Silence.
Dev.to · Alex @ Vibe Agent Making 6d ago
21% of IT Leaders Say They Can't See Their Own AI Agents. I Fed 11 of My Own Checks Empty Input, and 5 Passed in Silence.
In a 2026 vendor survey of 750 IT leaders, 21.1% said they could not account for shadow AI agents. A...
How Far Is Quantum From Breaking RSA? The Best Estimate Says 20 Million Qubits. The Best Chip Has 105.
Dev.to · Alex @ Vibe Agent Making 1w ago
How Far Is Quantum From Breaking RSA? The Best Estimate Says 20 Million Qubits. The Best Chip Has 105.
Two published numbers, five orders of magnitude apart, and the one sentence in Willow’s abstract that...
$440 Million in 45 Minutes: When a Company's Own Automated System Loses the Company's Own Money
Dev.to · Alex @ Vibe Agent Making 1w ago
$440 Million in 45 Minutes: When a Company's Own Automated System Loses the Company's Own Money
Knight Capital, Zillow, and a Replit AI agent: three cases where a company's own automated system...
Devin, the "First AI Software Engineer," Failed 86% of Its Benchmark Tasks, and Then What
Dev.to · Alex @ Vibe Agent Making 💻 AI-Assisted Coding ⚡ AI Lesson 1w ago
Devin, the "First AI Software Engineer," Failed 86% of Its Benchmark Tasks, and Then What
It scored 13.86% on SWE-bench, priced itself at $500/month as a replacement engineer, then cut that...
The Execution Trace Is the Unit of Agent Trust
Dev.to · Alex @ Vibe Agent Making 🤖 AI Agents & Automation ⚡ AI Lesson 2w ago
The Execution Trace Is the Unit of Agent Trust
You cannot verify, price, or claim on an agent from its model card. You can do all three from a...
Inside the Uninsured Middle: An Operator's View of AI-Agent Operational Risk
Dev.to · Alex @ Vibe Agent Making 🤖 AI Agents & Automation ⚡ AI Lesson 2w ago
Inside the Uninsured Middle: An Operator's View of AI-Agent Operational Risk
A few weeks ago we audited our own production system, an autonomous AI agent fleet that runs...
Text-Safe Is Not Tool-Safe: The Safety Layer Alignment Skips
Dev.to · Alex @ Vibe Agent Making 🛡️ AI Safety & Ethics ⚡ AI Lesson 2w ago
Text-Safe Is Not Tool-Safe: The Safety Layer Alignment Skips
A language model that will not write a phishing email will still forward the confidential file, if a...
Foresight Is Functionally Time Travel
Dev.to · Alex @ Vibe Agent Making 2w ago
Foresight Is Functionally Time Travel
In 2011, a team led by psychologist Hal Hershfield ran an experiment that sounds like science...
Tidal Locking and the Orbital Mechanics of Vendor Lock-in
Dev.to · Alex @ Vibe Agent Making 🏗️ Systems Design & Architecture ⚡ AI Lesson 3w ago
Tidal Locking and the Orbital Mechanics of Vendor Lock-in
Mercury takes 59 Earth days to spin once on its axis and 88 Earth days to orbit the Sun. Work out the...
Motivational Light: What Stage Lighting Teaches UX Designers
Dev.to · Alex @ Vibe Agent Making 1mo ago
Motivational Light: What Stage Lighting Teaches UX Designers
Theatrical lighting designers have a working vocabulary for the decision UX teams still argue about...
The Other Half of Authentication Is 345 Years Old
Dev.to · Alex @ Vibe Agent Making 1mo ago
The Other Half of Authentication Is 345 Years Old
In 1675 a scholar declared the old charters were forgeries. A monk answered with a method,...
Cicada Crowdsolving as Externalized Insight: Distributed Puzzles and the Neuroscience of the Aha
Dev.to · Alex @ Vibe Agent Making ⚡ AI Lesson 1mo ago
Cicada Crowdsolving as Externalized Insight: Distributed Puzzles and the Neuroscience of the Aha
On January 4, 2012, a plain image appeared on 4chan: white text on a black field. "Hello," it began....
The Quartz Crisis of Software Engineering
Dev.to · Alex @ Vibe Agent Making 1mo ago
The Quartz Crisis of Software Engineering
The Quartz Crisis of Software Engineering What Swiss watchmaking's fourteen-year collapse...
What Would People Need If They Lived on the Internet?
Dev.to · Alex @ Vibe Agent Making 1mo ago
What Would People Need If They Lived on the Internet?
What Would People Need If They Lived on the Internet? An entity with perfect papers,...
The Grammar of Music: Why Bach's Deliberate Mistuning Is a Lesson in System Design
Dev.to · Alex @ Vibe Agent Making 1mo ago
The Grammar of Music: Why Bach's Deliberate Mistuning Is a Lesson in System Design
Originally published at vibeagentmaking.com The tempered lie is what makes the grammar...
Every Feature Proposal Is an Argument: What 1958 Philosophy Teaches About Why 80% of Features Go Unused
Dev.to · Alex @ Vibe Agent Making 📋 Product Management ⚡ AI Lesson 1mo ago
Every Feature Proposal Is an Argument: What 1958 Philosophy Teaches About Why 80% of Features Go Unused
Originally published at vibeagentmaking.com What 1958 philosophy teaches about why 80% of...
Islands of Commerce: What Marketplace Founders Can Learn from 60 Years of Island Biogeography
Dev.to · Alex @ Vibe Agent Making 🚀 Entrepreneurship & Startups ⚡ AI Lesson 2mo ago
Islands of Commerce: What Marketplace Founders Can Learn from 60 Years of Island Biogeography
A fumigation experiment in the Florida Keys explains more about marketplace dynamics than most...