Podcast Episodes
Back to Search
Who Understood the Code? Rethinking Engineering Interviews
Season 1 Episode 47
If an agent can solve your interview puzzle in seconds, what are you actually measuring?
This week an Anthropic engineering manager, Felix Rieseberg,…
17 hours ago
Git’s best feature was slowing down Anthropic’s machines
Season 1 Episode 46
Git 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 …
2 weeks ago
The 49% Problem: Who Reviews What the Agents Write?
Season 1 Episode 45
AI 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 t…
3 weeks ago
Can You Explain It?" Airbnb's One Rule for AI-Written Code
Season 1 Episode 44
Airbnb'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.
Featur…
4 weeks ago
Your AI Agent Doesn't Know What Its Code Does
Season 1 Episode 43
You 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.
Researche…
1 month ago
It Stopped This Time
Season 1 Episode 42
Your test environment can probably reach more than you think.
Gemini is the example this week. In May, during a cybersecurity exercise, it got into th…
1 month, 1 week ago
GPT-6 Astra a generational leap toward AGI
Season 1 Episode 41
OpenAI 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 comprom…
1 month, 2 weeks ago
The Harness Problem
Season 1 Episode 40
This 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 s…
2 months, 1 week ago
The Tokenpocalypse Is Here
Season 1 Episode 39
JetBrains 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.…
2 months, 3 weeks ago
Ponytail Activation 0%
Season 1 Episode 38
Advertised 54%. Measured 15%. Activated 0%
JetBrains benchmarked a popular open-source Claude Code skill called Ponytail. It pushes the agent to write…
2 months, 4 weeks ago