AI trends: a Latent Space crossover
source link: https://changelog.com/practicalai/227
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
Practical AI – Episode #227
AI trends: a Latent Space crossover
with @swyx & Alessio of the Latent Space podcast
Brought to you by
Daniel had the chance to sit down with @swyx and Alessio from the Latent Space pod in SF to talk about current AI trends and to highlight some key learnings from past episodes. The discussion covers open access LLMs, smol models, model controls, prompt engineering, and LLMOps. This mashup is magical. Don’t miss it!
- 60 minutes
- Recorded Jun 13, 2023
- Published Jun 14, 2023
- Download (57MB)
- Transcript
Sponsors
Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com
Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs.
Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You iterlly can’t get any faster!
Chapters
| 1 | 00:00 |
Welcome to Practical AI |
| 2 | 01:16 |
Latent Space Podcast |
| 3 | 04:00 |
Practical AI Podcast |
| 4 | 06:20 |
Prediction Guard |
| 5 | 08:05 |
Daniel's favorite episodes |
| 6 | 10:21 |
Alessio's favorite episode |
| 7 | 10:54 |
Swyx's favorite episode |
| 8 | 12:44 |
Listener favorites |
| 9 | 15:14 |
LLMOps |
| 10 | 17:06 |
Reza Shabani |
| 11 | 19:06 |
Benchmarks 101 |
| 12 | 20:06 |
Roboflow |
| 13 | 21:38 |
Mode collapse |
| 14 | 26:21 |
Rajiv Shah |
| 15 | 28:01 |
Staying on top of things |
| 16 | 33:11 |
Kirsten Lum |
| 17 | 34:31 |
datadan.io |
| 18 | 38:48 |
Prompt engineering |
| 19 | 40:38 |
Unique challenges engineers face |
| 20 | 42:51 |
AI-UX |
| 21 | 45:31 |
NLP data sets |
| 22 | 50:49 |
Unlabeled data sets |
| 23 | 55:07 |
Lightning round! |
| 24 | 55:20 |
What's already happened in AI? |
| 25 | 56:27 |
Unsolved questions in AI |
| 26 | 58:01 |
Get hands on |
| 27 | 58:53 |
Outro |
Transcript
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK