Amber Teng - Building apps with a new generation of language models
Joining Jeremie Harris this episode is Amber Teng, a data scientist and TDS author (and former editor!) who recently published a blog that got quite a bit of attention, about a resume cover letter generator that she created using GPT-3, OpenAI's powerful and now-famous language model. They discussed the applied side of language modelling and prompt engineering, understanding how large language models have made new apps not only possible but also much easier to build, and the likely future of AI-powered products.
Intro music:
➞ Artist: Ron Gelinas
➞ Track Title: Daybreak Chill Blend (original mix)
➞ Link to Track: https://youtu.be/d8Y2sKIgFWc
0:00 Intro
2:30 Amber’s background
5:30 Using GPT-3
14:45 Building prompts up
18:15 Prompting best practices
21:45 GPT-3 mistakes
25:30 Context windows
30:00 End-to-end time
34:45 The cost of one cover letter
37:00 The analytics
41:45 Dynamics around company-building
46:00 Commoditization of language modelling
51:00 Wrap-up
Видео Amber Teng - Building apps with a new generation of language models канала Towards Data Science
Intro music:
➞ Artist: Ron Gelinas
➞ Track Title: Daybreak Chill Blend (original mix)
➞ Link to Track: https://youtu.be/d8Y2sKIgFWc
0:00 Intro
2:30 Amber’s background
5:30 Using GPT-3
14:45 Building prompts up
18:15 Prompting best practices
21:45 GPT-3 mistakes
25:30 Context windows
30:00 End-to-end time
34:45 The cost of one cover letter
37:00 The analytics
41:45 Dynamics around company-building
46:00 Commoditization of language modelling
51:00 Wrap-up
Видео Amber Teng - Building apps with a new generation of language models канала Towards Data Science
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Nicolas Miailhe - AI risk is a global problemYan Li - The surprising challenges of global AI philanthropyKevin Hu - Data observability and why it mattersTan Vachiramon - Choosing the right algorithm for your real-world problem (TDS Podcast - Clip)Danijar Hafner - Gaming our way to AGIBeena Ammanath - Defining trustworthy AIScaling Machine Learning | Razvan PeteanuPanel: Creative Ways to Collect & Use Data for AI | H. Ngo, S. Sun, H. Kontozopoulos, and R. TabriziGeorge Hayward: comedian, lawyer and data scientist (TDS Podcast - Clip)Explaining With Impact | Sheldon Fernandez and Michael St. JulesBen Garfinkel - Superhuman AI and the future of democracy and governmentLast Week In AI — 2021: The (full) year in reviewEliano Marques - The (evolving) world of AI privacy and data securityJoaquin Quinioñero-Candela - Responsible AI at FacebookIrina Rish - Out-of-distribution generalizationReal Talk with the Director of Data Science at Columbia UniversityNew to Data Visualization? Start with New York City | Thomas Hikaru ClarkMax Jaderberg - Open-ended learning at DeepMindKatya Sedova - AI-powered disinformation, present and futureStuart Armstrong - AI: Humanity's Endgame?Fail to Scale | Ian Scott