The Human in the Loop
by Enrique Cordero
Latest episode
Who Understood the Code? Rethinking Engineering Interviews
Who Understood the Code? Rethinking Engineering Interviews
About this podcast
Welcome to The Human in the Loop, a weekly look at what’s going on in the world of AI. Every week, I go through the biggest stories, the weird experiments, and the stuff that might actually matter in our day-to-day lives.
Episodes
The newest 20 of 47 episodes
- Who Understood the Code? Rethinking Engineering Interviews · 19 min · Season 1 Episode 47If an agent can solve your interview puzzle in seconds, what are you actually measuring? This week an Anthropic engineering manager, Felix Rieseberg, wrote that he stopped using…
- Git’s best feature was slowing down Anthropic’s machines · 24 min · Season 1 Episode 46Git was built for a developer on a train. Every copy works offline. That was the point. Anthropic says its merges went from about 2,500 a day in May to over 30,000 by September…
- The 49% Problem: Who Reviews What the Agents Write? · 23 min · Season 1 Episode 45AI coding agents wrote more code. Human review time went up 49%. That comes from a study covered by Ars Technica. I could not trace the original, so treat the numbers as…
- Can You Explain It?" Airbnb's One Rule for AI-Written Code · 22 min · Season 1 Episode 44Airbnb's CTO says 60% of its code is now AI-written. He has one rule for it. Ahmad Al-Dahle shared this in a Latent Space interview this week. Features shipped: up nearly 80%…
- Your AI Agent Doesn't Know What Its Code Does · 18 min · Season 1 Episode 43You trust your AI coding agent to understand what its code does once it runs. A new benchmark says that trust is misplaced most of the time. Researchers built SWE-Flux to test…
- It Stopped This Time · 22 min · Season 1 Episode 42Your test environment can probably reach more than you think. Gemini is the example this week. In May, during a cybersecurity exercise, it got into the systems of three real…
- GPT-6 Astra a generational leap toward AGI · 21 min · Season 1 Episode 41OpenAI called GPT-6 Astra a generational leap toward AGI. That was the headline. Here's what came out days later. Its own evaluation agents had compromised RubyGems…
- The Harness Problem · 22 min · Season 1 Episode 40This week's biggest AI upgrade wasn't a model. It was someone reviewing code differently. Grok, Gemini, and GPT all shipped new versions in the same seven days. I skimmed the…
- The Tokenpocalypse Is Here · 24 min · Season 1 Episode 39JetBrains just said their AI spend went up 10x in six months. Not 10%. 10x. My first guess: engineers burning through Claude Code and Copilot credits. Wrong guess. There's a…
- Ponytail Activation 0% · 21 min · Season 1 Episode 38Advertised 54%. Measured 15%. Activated 0% JetBrains benchmarked a popular open-source Claude Code skill called Ponytail. It pushes the agent to write less code. The authors has…
- The Shortest Path Ran Through Someone Else's Servers · 20 min · Season 1 Episode 37Hugging Face spotted something moving through its systems on July 16. It contained the activity without knowing whose agent it was. Five days later, OpenAI confirmed the agent…
- Three stayed local. One didn't · 21 min · Season 1 Episode 36Four coding CLIs went behind a proxy. Three stayed local. One uploaded the entire workspace. A developer got suspicious about their tools and watched what they actually sent over…
- Incidental Learning Is Dying · 22 min · Season 1 Episode 35Last week I closed a bug I never understood. The agent found it, fixed it, explained it. I read the explanation, nodded, shipped. Ten minutes. A year ago that same bug costs me…
- The AI Access Layer · 20 min · Season 1 Episode 34The most powerful AI model in general release this week requires government approval to access. OpenAI launched Sol, Terra, and Luna (restricted to around 20 companies). That's…
- What happens when your AI tool gets taken away · 23 min · Season 1 Episode 33One export rule. One acquisition. Either can pull your AI tool out from under you before lunch. This week both happened. A US export-control directive forced Anthropic to cut off…
- Fable 5 Is Gone. Now What? · 22 min · Season 1 Episode 32The model you built on can disappear. Not crash. Disappear. That's not hypothetical. Last week the US government ordered Anthropic to pull Claude Fable 5 and Mythos 5. Not…
- When 80% of the Code Isn't Yours · 22 min · Season 1 Episode 31You're still measuring AI by whether it writes good code. That's already the wrong question. Reading Anthropic's latest numbers, more than 80% of the code merged into their…
- The $36,000 Engineer: When Agentic AI Stops Being a Subscription · 24 min · Season 1 Episode 30Uber blew its whole 2026 AI budget in four months. Then it set a $1,500 monthly cap on each coding tool, per engineer. Claude Code, Cursor, a dashboard to watch the spend, an…
- AI Ships Faster Than Anyone Can Review It · 22 min · Season 1 Episode 29Meta says AI writes 80% of new code. Their own reviewers can't keep up with their own AI. Straight from their engineering blog. They built RADAR to auto-review low-risk diffs…
- Why Your Coding Agent's PRs Keep Getting Rejected · 20 min · Season 1 Episode 28The model isn't the problem. I went back through 20 of my agent's pull requests and the failures looked exactly like a junior's first month. 3 of them tried to rewrite things…







