Hardware Podcasts

Pragmatic LLM usage with Nicholas Carlini

Oxide and Friends · 9 Aug 2024 · 1h 33m · Episode 20

What this episode covers

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.

Most relevant to

makers and hobbyists

Topics

Mentioned

Companies
Khan Academy
Tools
Emacs, Clap
Also
GPT-4, Claude 3.5 Sonnet, Rust, Python, ChatGPT, Siri, Sal Khan

Related episodes from other shows

Other shows on the same ground, closest first.

  • 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

  • Built 2 Scale · 1h 05m

    Claude Opus 4.5 Coding Revolution, Apple Partners With Google Gemini & Meta Acquires Manus for $5B

    Hosts Matt Perrott and Scott Wilcox discuss the 2026 AI landscape, highlighting Claude Opus 4.5 and Claude Code as watershed moments for coding dominance, with examples from Shopify's Toby Lutke and Andre Karpathy. They analyze major industry shifts, including Apple's partnership with Google to power Siri with Gemini and Meta's $5 billion acquisition of Manus. The episode concludes with a 'Tool of the Week' segment where Scott builds a personalized baby word tracking app in a weekend using Vibe Coding, illustrating the rise of on-demand personal software.

    AI & machine learningMicrocontrollers & dev platforms
    9 chapters

  • The Next Byte Podcast · 28m

    125. Prompt Engineering: Latest Meme or The Next Big Thing?

    Hosts Daniel and Forbode discuss whether prompt engineering is a legitimate career or a passing meme, analyzing the skills required to effectively interface with generative AI models like ChatGPT and Midjourney. They compare the iterative nature of prompt engineering to learning a new programming language or using calculators in math, arguing that it accelerates productivity rather than replacing human critical thinking. The hosts highlight the rapid adoption of generative AI, citing ChatGPT's user growth and revenue projections, and note job openings at companies like OpenAI and in the federal government.

    AI & machine learningCareers & education
    8 chapters

  • IoT For All Podcast · 20m

    Large Language Models and How To Use Them | Cyrano.ai's Scott Sandland | Internet of Things Podcast

    Scott Sandland, Founder and CEO of Cyrano.ai, explains that Large Language Models (LLMs) are essentially advanced autocomplete systems that predict the next word based on massive datasets, making natural language the new interface for computing. He argues that while LLMs accelerate execution, the 'move fast and break things' philosophy is dangerous for AI due to unpredictable ethical outcomes and biases, necessitating a parallel 'ethics roadmap' alongside technical development. Sandland highlights Cyrano.ai's proprietary API, which uses linguistic analysis to assess empathy and relationship value in contexts like sales and mental health, rather than relying on generic sentiment analysis.

    AI & machine learningSecurity & privacy
    6 chapters

  • Embedded.fm · 1h 08m

    502: Chat, J'ai Peté!

    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.

    AI & machine learningEmbedded firmware
    6 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.