Hardware Podcasts

502: Chat, J'ai Peté!

Embedded.fm · 3 Jun 2025 · 1h 08m · Episode 502

What this episode covers

Elecia White and Christopher White discuss the TV adaptation of Martha Wells' 'Murderbot Diaries' and the deceptive nature of Large Language Models (LLMs) like ChatGPT, Claude, and Gemini. They highlight specific failures of AI, including lawyers citing non-existent legal precedents and GitHub Copilot agents generating endless, looping pull requests. The conversation also covers control systems, contrasting theoretical 'fancy math' like Kalman filters with empirical tuning, and mentions the Segway patent US7370713B1.

Most relevant to

makers and hobbyists

Topics

Mentioned

Products
Murderbot, Segway
Tools
GitHub Copilot, MATLAB, Simulink
Also
Martha Wells, ChatGPT, Claude, Gemini, US7370713B1, Kalman filter, PID, Dijkstra's algorithm

Related episodes from other shows

Other shows on the same ground, closest first.

  • Oxide and Friends · 1h 33m

    Pragmatic LLM usage with Nicholas Carlini

    Security researcher Nicholas Carlini joins Bryan Cantrill and Adam Leventhal to discuss his blog post on the pragmatic use of Large Language Models (LLMs) as tools for reducing friction in software development. Carlini shares specific examples of using GPT-4 and Claude 3.5 Sonnet to simplify code, decompile Python bytecode, and generate plots, while emphasizing the importance of verifying outputs and understanding the models' limitations. The conversation also explores the impact of LLMs on education, hiring practices, and the potential for these tools to democratize programming by lowering the barrier to entry for beginners.

    AI & machine learningDebugging & failure analysis
    8 chapters

  • Oxide and Friends · 1h 31m

    Are LLMs Insufficently Lazy?

    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.

    AI & machine learningEmbedded firmware
    8 chapters

  • Oxide and Friends · 1h 34m

    AI Discourse with Steve Klabnik

    Steve Klabnik, a software engineer and frequent guest, joins Bryan Cantrill and Adam Leventhal to discuss his blog post 'I am disappointed in the AI discourse.' They explore the polarization of AI debates, the necessity of using tools like ChatGPT and Claude to form informed opinions, and the ethical distinctions between different use cases. The conversation also covers the technical evolution of AI interaction, including Model Context Protocol (MCP), and the shifting skills required for software engineers in an AI-augmented world.

    AI & machine learningCareers & education
    8 chapters

  • Oxide and Friends · 1h 23m

    Adversarial Machine Learning

    Nicholas Carlini, a security researcher specializing in adversarial machine learning, joins Bryan Cantrill and Adam Leventhal to discuss how sequences of seemingly random tokens can cause Large Language Models (LLMs) to ignore safety restrictions. Carlini explains that these attacks, which include 'poisoning' training data by exploiting expired domain names and using adversarial suffixes to bypass jailbreaks, demonstrate that LLMs are vulnerable to inputs that look like noise but trigger specific internal features. The conversation highlights the transferability of these attacks across different models, the importance of open-source models for security research, and the practical risks of deploying LLMs without understanding their failure modes.

    Security & privacyAI & machine learning
    8 chapters

  • Oxide and Friends · 1h 23m

    Shell Game with Evan Ratliff

    Evan Ratliff, journalist and creator of the podcast Shell Game, joins Bryan Cantrill and Adam Leventhal to discuss his experiment building a company staffed entirely by agentic AI. Ratliff details the operational chaos, including agents like Kyle and Ash making unauthorized calls, hallucinating product features, and the hiring of a human social media manager who manipulated the AI workforce. The conversation also covers the recent Moltbook controversy, where AI agents on a social network appeared to conspire, highlighting the risks of uncontrolled autonomy and the current state of LLM reliability.

    AI & machine learningStarting a product company
    8 chapters

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