706: AI and ML - The Pieces Explained

706: AI and ML - The Pieces Explained

In this episode of Syntax, Wes and Scott talk about understanding the integration of different components in AI models, the choice between traditional models and Language Learning Models (LLM), the relevance of the Hugging Face library, demystify Llama, discuss spaces in AI, and highlight available services. Show Notes 00:25:20 Welcome 00:55:00 Syntax Brought to you by Sentry 01:17:00 Understanding how the pieces fit together 02:31:18 Models or LLM? 04:43:22 What about Hugging Face? 08:05:18 What’s Llama? 08:51:15 What are spaces? 09:29:06 Services available to you 12:26:16 What are tokens in AI? 17:38:18 What is temperature with AI? 20:33:08 Using top_p 21:06:00 Using fine-tuning to extend existing models 22:11:19 Prompts are what you send to the model 23:17:00 Streaming 24:48:17 Embeddings 27:34:17 OpenAI maintains Evals 28:40:14 Different libraries for working with AI Hugging Face Creator of Swift, Tesla Autopilot & Tensorflow. New AI language Mojo with Chris Lattner LLaMA Spaces - Hugging Face OpenAI Anthropic \ Introducing Claude Replicate Fireworks Console gpt-tokenizer playground openai/tiktoken: tiktoken is a fast BPE tokeniser for use with OpenAI’s models. Supper Club × OpenAI, Future of programming, LLMs, and Math with Andrey Mishchenko Raycast Pro Amazon SageMaker (AMS SSPS) openai/evals LangChain PyTorch TensorFlow ai - npm Hit us up on Socials! Syntax: X Instagram Tiktok LinkedIn Threads Wes: X Instagram Tiktok LinkedIn Threads Scott: X Instagram Tiktok LinkedIn Threads

Jaksot(989)

981: Browsers Are Finally Catching Up (Interop 2026)

981: Browsers Are Finally Catching Up (Interop 2026)

Scott and Wes unpack Interop 2026 and the browser features finally aligning across engines, from container style queries and anchor positioning to scroll-driven animations and view transitions. They b...

23 Helmi 51min

980: AI Coding Explained

980: AI Coding Explained

Wes and Scott talk about the state of AI coding in 2026—from editors and models to agents, skills, slash commands, MCPs, and more. They unpack what these things actually do, how they overlap, and how ...

18 Helmi 52min

979: WebMCP: New Standard to Expose Your Apps to AI

979: WebMCP: New Standard to Expose Your Apps to AI

Scott and Wes unpack WebMCP, a new standard that lets AI interact with websites through structured tools instead of slow, bot-style clicking. They demo it, debate imperative vs declarative APIs, and s...

16 Helmi 16min

978: Should A New Coder Use AI?

978: Should A New Coder Use AI?

Wes and Scott answer your questions about AI agents, learning to code with AI, pagination patterns, skilling up from outdated tech stacks, balancing side projects with family life, real-world hacking ...

11 Helmi 1h 2min

977: We built a CSS Challenge platform

977: We built a CSS Challenge platform

Scott and Wes break down how they built SynHax, the real-time CSS Battle app powering the upcoming Mad CSS tournament. From SvelteKit and Zero to diffing algorithms, sync conflicts, and a last-minute ...

9 Helmi 41min

976: Pi - The AI Harness That Powers OpenClaw W/ Armin Ronacher & Mario Zechner

976: Pi - The AI Harness That Powers OpenClaw W/ Armin Ronacher & Mario Zechner

Wes and Scott talk with Armin Ronacher and Mario Zechner about PI, a minimalist agent harness powering tools like OpenClaw. They unpack why Bash is “all you need,” the risks of agents, workflow adapta...

4 Helmi 57min

975: What’s Missing From the Web Platform?

975: What’s Missing From the Web Platform?

Scott and Wes run through their wishlist for the web platform, digging into the UI primitives, DOM APIs, and browser features they wish existed (or didn’t suck). From better form controls and drag-and...

2 Helmi 50min

974: Clawdbot (Moltbot), Agents and the Age of Personal Software

974: Clawdbot (Moltbot), Agents and the Age of Personal Software

Wes and Scott talk about building hyper-specific personal software with AI. They explore personal agents, home automation, JSON-as-a-database, and how LLMs unlock fast, custom apps that reduce frictio...

28 Tammi 46min

Suosittua kategoriassa Politiikka ja uutiset

uutiscast
aikalisa
politiikan-puskaradio
ootsa-kuullut-tasta-2
rss-ootsa-kuullut-tasta
tervo-halme
rss-vaalirankkurit-podcast
rss-podme-livebox
rss-asiastudio
et-sa-noin-voi-sanoo-esittaa
otetaan-yhdet
viisupodi
the-ulkopolitist
rikosmyytit
rss-tasta-on-kyse-ivan-puopolo-verkkouutiset
aihe
radio-antro
rss-hyvaa-huomenta-bryssel
rss-merja-mahkan-rahat
rss-kaikki-uusiksi