Logo
    Search

    language_models

    Explore "language_models" with insightful episodes like "Context windows, computer constraints, and energy consumption with Sarah and Elad" and "728: AI Superpowers with Kevin Hou and Codeium" from podcasts like ""No Priors: Artificial Intelligence | Machine Learning | Technology | Startups" and "Syntax - Tasty Web Development Treats"" and more!

    Episodes (2)

    Context windows, computer constraints, and energy consumption with Sarah and Elad

    Context windows, computer constraints, and energy consumption with Sarah and Elad
    This week on No Priors hosts, Sarah and Elad are catching up on the latest AI news. They discuss the recent developments in AI music generation, and if you’re interested in generative AI music, stay tuned for next week’s interview! Sarah and Elad also get into device-resident models, AI hardware, and ask just how smart smaller models can really get. These hardware constraints were compared to the hurdles AI platforms are continuing to face including computing constraints, energy consumption, context windows, and how to best integrate these products in apps that users are familiar with.  Have a question for our next host-only episode or feedback for our team? Reach out to show@no-priors.com Follow us on Twitter: @NoPriorsPod | @Saranormous | @EladGil  Show Notes:  (0:00) Intro (1:25) Music AI generation (4:02) Apple’s LLM (11:39) The role of AI-specific hardware (15:25) AI platform updates (18:01) Forward thinking in investing in AI (20:33) Unlimited context (23:03) Energy constraints

    728: AI Superpowers with Kevin Hou and Codeium

    728: AI Superpowers with Kevin Hou and Codeium

    In this supper club, Scott and Wes welcome Kevin Hou, Head of Product Engineering at Codeium, a blazing fast AI-powered code completion and chat tool for developers.

    Show Notes

    • 00:00 Welcome to Syntax!
    • 05:31 An introduction to Codeium.
    • 07:56 What information are you sending the AI to get such good completions?
    • Codeium compliance
    • 09:15 Codeium runs a 'Language Server'.
    • 11:15 Crawling dependency tree and abstract syntax tree.
    • 12:07 Using Codeium Live.
    • 12:34 How big of a codebase can you run this on?
    • 14:39 Sending select amounts of data to AI.
    • 16:06 Does Codeium maintain codebase preferences and styling (ie. snake case)?
    • 17:39 Will Codeium scan the dependency?
    • 19:23 AI UI, have we found the best format?
    • 21:55 Crazy ideas in tech.
    • 22:53 Additional AI UI inputs.
    • 24:14 How do you make an AI model?
    • 28:42 How does Codeium manage the product roadmap?
    • 32:09 Do AI models get worse over time? How does Codeium validate that it's not?
    • Open AI Evals
    • 35:39 How is Codeium THAT fast?
    • 36:49 What programming langauges does Codeium use?
    • 38:55 Codeium Playground.
    • Codeium Playground
    • 39:15 Caching as a performance improvement.
    • 39:58 What is the pipe between Codeium and editor?
    • 40:17 Codeium chat service.
    • 41:44 A WebSocket system allowing push and pull communication.
    • 43:13 Closed Beta for GPT 4.0.
    • 46:12 The dreaded closing quote bug.
    • 48:26 Sometimes bugs bug Wes.
    • 49:49 Supper Club Questions
    • 51:40 Perplexity.ai
    • 52:35 What editor does Kevin use?
    • 55:31 Sick Picks + Shameless Plugs

    Sick Picks

    Shameless Plugs

    Hit us up on Socials!

    Syntax: X Instagram Tiktok LinkedIn Threads

    Wes: X Instagram Tiktok LinkedIn Threads

    Scott: X Instagram Tiktok LinkedIn Threads

    Randy: X Instagram YouTube Threads