Hardware Podcasts

Are LLMs Insufficently Lazy?

Oxide and Friends · 3 May 2026 · 1h 31m · Episode 8

What this episode covers

Bryan Cantrill and Adam Leventhal of Oxide Computer Company are joined by software engineer Gregoirein to critique Y Combinator CEO Garry Tan’s claim of writing 37,000 lines of code daily using LLMs. Gregoirein used Claude to audit Tan’s public projects, revealing broken assets, legal non-compliance, and a site outage, while the hosts discuss the 'peril of laziness' and the difference between generating code and engineering elegant systems. They argue that while LLMs are useful for review or low-stakes tasks, they cannot replace the deep thinking required for complex, high-consequence software like kernel linkers or signal handlers.

Most relevant to

early-stage companies

Topics

Mentioned

Companies
Oxide Computer Company, Y Combinator
Products
Garry's List, Gstack
Tools
Claude, DTrace
Also
Garry Tan, ZFS, Java, USDT

Related episodes from other shows

Other shows on the same ground, closest first.

  • The Pragmatic Embedded Podcast · 55m

    Crossover with Embedded AI Podcast

    Jeff Gable, Luca, and Ryan Torvik discuss integrating Large Language Models (LLMs) into embedded systems engineering workflows, emphasizing that AI must augment rather than replace rigorous engineering discipline. They identify 'vibe coding' as a critical anti-pattern where developers lose control of architectural decisions by letting AI generate too much code at once, leading to unmanageable outputs and hallucinations. The hosts advocate for strict context management, test-driven development (TDD), and small, incremental commits to maintain deterministic quality, particularly in safety-critical domains like medical devices and automotive systems. They conclude that while LLMs accelerate prototyping and boilerplate generation, human code review and ownership remain non-negotiable for reliable production software.

    Embedded firmwareDebugging & failure analysis
    8 chapters

  • The Pragmatic Embedded Podcast · 28m

    AI-enhanced Embedded Development (May 2025 Edition)

    Luca, an embedded software expert, discusses his experience at the Embedded Online Conference and a German conference, highlighting an LLM-only hackathon where participants were forbidden from writing code manually. He explains that effective AI-assisted development requires rigorous context management, treating prompts like version-controlled code, and managing external context files to prevent hallucinations. The conversation covers the economic benefits of AI (approx. $0.01 per line of code), the tightening of feedback loops, and the evolving role of developers from coders to AI supervisors and technical product owners.

    Embedded firmwareAI & machine learning
    7 chapters

  • Coredump Sessions · 55m

    #007: AI, Open Source, and the Future of Embedded Development: How Much Code Will We Actually Write?

    François Baldassari, CEO of Memfault, and Thomas Sarlandie, Field CTO of Memfault, host a panel with Jonathan Beri, CEO of Golioth, and Dan Mangum, CTO of Golioth, to discuss the intersection of AI, open source, and embedded development. The group analyzes the maturity of edge AI for audio and video processing, the challenges of integrating LLMs into hardware due to rapid model iteration, and the current state of using AI for firmware development. They conclude that while AI is transforming code generation and review, open source remains critical for training models and providing trusted, complex infrastructure like Zephyr and FreeRTOS.

    Embedded firmwareAI & machine learning
    9 chapters

  • Being an Engineer · 57m

    S4E43 Kevin Surace | How To Use AI For Engineering

    Kevin Surace, an AI keynote speaker and founder of Appvance, explains that large language models are statistical tools that amplify human intelligence rather than replace it, comparing them to calculators for language. He argues that AI will increase productivity, potentially leading to shorter workweeks, and helps engineers by generating novel design ideas, writing code, and improving quality assurance through computer vision. Surace emphasizes that while AI is not yet good at designing complex machinery, it excels at processing vast amounts of technical data to suggest solutions and automate routine tasks. He advises engineers to use AI as a co-pilot for communication, coding, and creative problem-solving to overcome skill gaps and accelerate their careers.

    AI & machine learningEmbedded firmware
    9 chapters

  • Embedded.fm · 1h 05m

    53: Being a Grownup Engineer (Repeat)

    Jack Ganssle, author of 'The Art of Designing Embedded Systems' and 'The Embedded Systems Dictionary', argues that embedded software development has failed to adopt true engineering discipline, relying on 'heroics' rather than process. He cites the Toyota unintended acceleration case, where Michael Barr identified 11,000 global variables, as evidence of the catastrophic costs of poor software practices. Ganssle advocates for rigorous requirements gathering, static analysis tools like LDRA and Spark, and metrics-driven benchmarking to reduce debugging time and improve code quality. He contrasts this disciplined approach with the 'hacker' and 'maker' cultures, emphasizing that safety-critical systems require proven processes rather than ad-hoc coding.

    Embedded firmwareDebugging & failure analysis
    10 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Oxide and Friends. The episode itself belongs to its publisher.