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,…
3 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 …
1 week, 6 days 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