789: Do More With AI - LLMs With Big Token Counts

Syntax - Tasty Web Development Treats

Wes Bos

Tech News, News, Technology

4.9 • 1.2K Ratings

🗓️ 1 July 2024

⏱️ 34 minutes

🔗️ Recording | iTunes | RSS

🧾️ Download transcript

Summary

Join Scott and CJ as they dive into the fascinating world of AI, exploring topics from LLM token sizes and context windows to understanding input length. They discuss practical use cases and share insights on how web developers can leverage larger token counts to maximize the potential of AI and LLMs. Show Notes 00:00 Welcome to Syntax! 01:31 Brought to you by Sentry.io. 02:42 What is a token? Quizgecko GPT-4 Token Counter. 04:22 Context window sometimes called “max tokens”. OpenAI Platform Models. Claude Models. 10:42 Understanding input length. 11:59 Models + services with big token counts. Gemini Docs. 13:22 Generating open API documentation for a complex API. 17:29 Generating JSDoc style typing. Drop-In stolinski GitHub. 21:07 Generating seed data for a complex database. bytedash w3cj GitHub. 24:34 Summarizing 8+ hours of video. 29:35 Some things we’ve yet to try. 31:32 What about cost? Google AI for Developers Cost. Hit us up on Socials! Syntax: X Instagram Tiktok LinkedIn Threads Wes: X Instagram Tiktok LinkedIn Threads Scott: X Instagram Tiktok LinkedIn Threads CJ: X Instagram YouTube TwitchTV Randy: X Instagram YouTube Threads

Transcript

Click on a timestamp to play from that location

0:00.0	Welcome to Syntax. On this Monday Hastie Treat, we're going to be talking about
0:06.0	L.L. M's large language models with a greater context window or greater amount of
0:11.5	tokens that you can use and why that makes a difference and
0:15.1	what you can possibly do with that given your software developer and well we kind of work with a lot of
0:20.7	text right so you might think that these tokens are advantageous
0:24.6	to have more of.
0:25.5	And that's definitely the case.
0:26.9	So we're going to be talking a little bit about AI
0:29.6	solutions that can help you in your development
0:32.1	just because you can give them more data and why that matters.
0:36.2	My name is Scott Tolinsky. I'm a developer from Denver and with me today once again is CJ.
0:42.0	What's up CJ? Not much, how you doing Scott?
0:45.0	Oh, I'm doing good. Just a, you know, context here. We just came back out of our holiday weekend. I was doing some grilling, some dad stuff. I was at the pool, I was
0:55.6	grilling, made some ribs. I know you're not not a meat guy, but man, CJ I'm
1:00.4	the West Boss myself, he's a he's definitely a grill master. I'm a grill
1:05.3	novice here but I made some pretty day good rib so I'm a little proud of myself for
1:10.5	doing that Memorial Day thing. How are you doing?
1:14.0	Pretty good. Yeah, we had a little get-together on Saturday and I grilled some plant-based burgers and
1:18.6	Peked Bratz, which is really good. The weather here has been awesome and it's fun to just
1:24.4	chill and grill for sure.
1:25.9	Chill and grill. I love it. We're going to be chilling and grilling today on
1:30.4	syntax, but before we do, let's talk a little bit about some really neat AI features
	...

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.