Software Engineering Daily

Over the past couple of years, companies raced to get their employees using AI, often encouraging them to lean on it as much as possible. However, as AI coding tools spread through engineering teams, many companies watched their AI bills explode. That kind of runaway cost growth can threaten a business, so the new challenge is capturing the productivity gains from AI without the spending spiraling out of control.

Databricks is a data and AI company that hit this problem early, running AI tools across thousands of its own engineers. Rather than clamp down on usage, the team built a set of practical ways to manage the cost, from taking advantage of steadily falling model prices to automatically routing each request to the cheapest model that can still do the job well.

Patrick Wendell is a co-founder of Databricks, where he leads engineering teams and has driven much of the company’s internal AI adoption. He recently wrote a viral blog post on managing AI coding costs that reached the top of Hacker News. In this episode, Patrick joins Kevin Ball to discuss why AI costs suddenly exploded, the main levers companies have to bring them under control, the trade-offs between managing costs on the server versus in the developer’s tools, and why the next big challenge is giving AI the right context about how a company actually works.

Sponsorship inquiries:
sponsor@softwareengineeringdaily.com

The post Managing AI Coding Costs at Scale appeared first on Software Engineering Daily.

Codebases in enterprise organizations often span hundreds of thousands, or even millions, of lines of code. In many cases, changes must follow established patterns precisely, or risk introducing costly security or operational issues. A common challenge with AI coding tools is that they struggle at this scale: LLM context windows cover only a fraction of a large codebase, and output quality degrades the longer an agent runs.

Blitzy is an autonomous software development platform for the enterprise. It starts by understanding your entire codebase, building a knowledge graph that acts as a shared source of truth. From a well-defined spec that engineers review and approve, it orchestrates specialized agents that work in parallel to build, review, and test code autonomously at scale. The result is a pull request that engineers can then review and merge

Sid Pardeshi is the CTO and co-founder of Blitzy, and he previously worked at NVIDIA. In this episode, he joins Kevin Ball to discuss why large codebases break today’s coding agents, how a knowledge graph extends what models can reason about, how a reviewable plan keeps specialized agents aligned, and where autonomous software development is headed.

Full Disclosure: This episode is sponsored by Blitzy

Sponsorship inquiries:
sponsor@softwareengineeringdaily.com

The post Blitzy and Autonomous Software Development for Enterprise appeared first on Software Engineering Daily.

In recent years, the main impact of AI has been on the digital world, and most notably software engineering. However, its longer-term effect on the physical world may prove even more profound, reshaping how cars drive themselves, how factories run, and how robots move through homes and warehouses.

World models are at the center of the movement to bring AI into the physical space. These models take in observations of the current state of the world and predict what comes next, which lets a robot plan its next move or a car anticipate the road ahead. NVIDIA has been building a family of these models called Cosmos, and sits at the frontier of physical AI and robotics.

Amit Goel has been at NVIDIA for fifteen years, and he is currently the Head of Robotics Ecosystem and Edge AI Product. In this episode, Amit joins Matt Merrill to discuss what separates physical AI from digital AI, how world models plan and predict, the two-tower architecture that lets a robot reason and act at once, why training on video demanded a new data pipeline, and how any developer can start building in this space.

Free Physical AI Courses: https://nvda.ws/4xqCfo9
Cosmos: https://nvda.ws/4zJ4iRj
GR00T Teleop + LeRobot: https://huggingface.co/blog/nvidia/nvidia-isaac-teleop-and-gr00t17-in-lerobot

Sponsorship inquiries:
sponsor@softwareengineeringdaily.com

The post Physical AI at NVIDIA appeared first on Software Engineering Daily.

Software testing is widely understood as essential to building reliable systems, and it’s one of the hardest things to get right. A fundamental issue is that tests are good at confirming the behavior a team expects, but the most damaging failures tend to hide in the edge cases no one thought to check during development. Those blind spots are only growing as AI produces more code that no human has closely reviewed.

Antithesis is a software verification company built around an approach called deterministic simulation testing. The platform runs a customer’s software in a fully controlled environment, exploring thousands of different paths through it at runtime. Crucially, the paths aren’t pre-specified and they’re not merely the expected cases. In this way, it can surface rare, damaging bugs that normal testing would never catch.

Carl Sverre is on the Red Team at Antithesis and he also leads much of the company’s AI strategy. In this episode, Carl joins Sean Falconer to discuss the Antithesis approach to software verification, why reliability tooling has been chronically underinvested, what makes stateful and distributed systems so hard to test, how deterministic simulation testing works under the hood, and much more.

Full Disclosure: This episode is sponsored by Antithesis

Sponsorship inquiries:
sponsor@softwareengineeringdaily.com

The post Software Verification in the Age of Coding Agents appeared first on Software Engineering Daily.

SED News is a monthly podcast from Software Engineering Daily where hosts Gregor Vand and Sean Falconer break down the biggest stories shaping software engineering, Silicon Valley, and the broader tech industry.

In this episode, Gregor and Sean cover a wave of new product drops, including Jev from TypeSafe AI, a model that returns scored, type-safe structured responses for machine-to-machine tasks like routing and classification rather than human-style chat. They also dig into Meta‘s Muse, a personal AI assistant with a companion keychain device, and the upcoming IPO of Nscale, a former crypto-mining outfit turned “neocloud” inference provider whose filing leans heavily on a single unnamed customer.

The main topic examines the tension around AI risk, frontier lab slowdowns, and the conspiracy theories they’ve spawned. Gregor and Sean unpack Dario Amodei’s essay on pacing AI development, the awkward timing of major model launches days later, and whether calls to slow down are genuine safety concerns or a way for incumbents to protect their market position, weighing it all against the long history of how society has absorbed transformative technologies.

As always, the episode wraps up with a few standout Hacker News threads, including a labor-of-love effort to restore the original cut of a classic film, and a vibe-coded local AWS testing harness that raised a few eyebrows in the comments.

Sponsorship inquiries:
sponsor@softwareengineeringdaily.com

The post SED News: Jev, Meta’s Muse, and the AI Slowdown Paradox appeared first on Software Engineering Daily.