Podcasts | Dev Interrupted by LinearB

Featured

Goblins in prod, the messy middle of AI adoption, and everything is a harness now

Andrew and Ben unpack the "Goblin Invasion" postmortem at OpenAI and the security risks of agentic intention drift. Explore the "Messy Middle" of AI adoption,...

Teach the primitives or watch your competitor define them | Baseten’s Philip Kiely

Baseten’s Philip Kiely breaks down why Inference Engineering is the next critical discipline for AI teams and why education is the ultimate market development...

Tokemaxxing scoreboards, the vegan LLM from before 1931, and 30% of the web is now AI-generated

Andrew and Ben unpack the era of "tokenmaxxing" scoreboards, GitHub Copilot’s transition to usage-based billing, and the terrifying production wipeout by a...

Giving robots a brain | Intrinsic’s Brian Gerkey

Intrinsic CTO Brian Gerkey explains how modern AI is giving industrial robots "brains" to handle physical unpredictability, detailing the shift to software-defi...

Real conversations with top engineering leaders every week

LinearB may send you email occasionally about how you can optimize productivity. We will not share your information with anyone. Ever.

The harness is the showdown, the humans are the tool calls, and have you seen my Claude Code buddy?

Andrew and Ben unpack the chaos of AI token pricing, the Vercel security breach, and the massive Claude Code leak that exposed 12 game-changing architecture...

The best model for your team? You haven’t invented it yet. | Ai2’s Tim Dettmers

Ai2’s Tim Dettmers explains how to build state-of-the-art coding agents using minimal resources, revealing how the SERA model out-specializes frontier models...

The self-authoring wiki, beating brain fry, and Obsidian as memory is a trap

This week on Friday Deploy, Andrew and Ben explore the cognitive toll of managing AI agent swarms and share Kelly Vaughn's burnout prevention strategies.

The guardian in the machine | Wayfound’s Tatyana Mamut

Wayfound AI CEO Tatyana Mamut explains why traditional software testing fails when applied to stochastic AI models, detailing how "guardian agents" are...

Reading model benchmarks like a pro, Mythos is looming, and Claude talk caveman, save big token

Andrew and Ben explore the "Caveman" prompting hack that slashes token costs by 65%, Anthropic’s $100M Project Glasswing security play, and the release of...

Stop measuring AI adoption. Start measuring AI impact. | LinearB’s APEX framework

LinearB COO Dan Lines joins the show to reveal APEX, a new engineering operating model designed to help leaders stop measuring AI adoption and start measuring...

2 3...34

Dev Interrupted