706: AI and ML - The Pieces Explained

Syntax - Tasty Web Development Treats

Wes Bos

Tech News, Technology, News

4.9 • 1.2K Ratings

🗓️ 18 December 2023

⏱️ 33 minutes

🔗️ Recording | iTunes | RSS

🧾️ Download transcript

Summary

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

Transcript

Click on a timestamp to play from that location

0:00.0	Monday, Monday, Monday, Monday, open wide Dev fans.
0:04.0	Get ready to stuff your face with JavaScript,
0:07.0	CSS, node modules, barbecue tips, get workflows,
0:10.0	break dancing, soft skills, web development,
0:12.0	the hastyest, the craziest, the craziest, the tastiest, web development
0:16.4	treats.
0:17.4	Coming in hot, here is Wes, Barracuda, Bars, and Scott, El Tor Toroloko Tolinsky.
0:25.0	Welcome to Syntax in this Monday.
0:31.0	Hasty Treat.
0:32.0	We're going to be talking about jargon and we're going to be talking about AI jargon.
0:38.0	You've seen these things around you've heard the terms and we're going to be talking about all of the pieces of AI and
0:45.0	machine learning and we're going to explain what the heck these things are so that
0:49.5	way the next time you see somebody say something you might have a clue what it is.
0:55.0	And just like that anytime you're exploring anything new, it's important to have
0:59.5	some sort of companion with you, a companion that can save you from errors and bugs, help you with performance,
1:05.6	help you with all kinds of things, maybe even get user feedback.
1:08.4	I'm talking about a tool like Century.
1:10.0	At Century.io, use the coupon code, tasty treat, all all lowercase all one word to get two months for free.
1:15.5	So let's get into it Wes. Yes. So this is basically having been
1:22.3	working with AI stuff for probably about a year now, there was a lot of
1:27.1	words that I didn't necessarily understand and not necessarily just the words but
1:32.4	how do the pieces fit together?
	...

Please login to see the full transcript.

Previous episode | Next episode

Disclaimer: The podcast and artwork embedded on this page are from Wes Bos, and are the property of its owner and not affiliated with or endorsed by Tapesearch.

Generated transcripts are the property of Wes Bos and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.