Mental Models for Advanced ChatGPT Prompting with Riley Goodside - 652

Описание: Today we’re joined by Riley Goodside, staff prompt engineer at Scale AI. In our conversation with Riley, we explore LLM capabilities and limitations, prompt engineering, and the mental models required to apply advanced prompting techniques. We dive deep into understanding LLM behavior, discussing the mechanism of autoregressive inference, comparing k-shot and zero-shot prompting, and dissecting the impact of RLHF. We also discuss the idea that prompting is a scaffolding structure that leverages the model context, resulting in achieving the desired model behavior and response rather than focusing solely on writing ability.

🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confi...


🗣️ CONNECT WITH US!
===============================
Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/
Join our Slack Community: https://twimlai.com/community/
Subscribe to our newsletter: https://twimlai.com/newsletter/
Want to get in touch? Send us a message: https://twimlai.com/contact/


📖 CHAPTERS
===============================
00:00 - Research journey
05:49 - Douglas Hofstadter article
08:23 - Exploring prompting to reduce hallucinations
13:20 - LLM mental models and sentience
17:38 - ‘Model is an expert’ technique
20:24 - K-shot vs zero-shot prompting
25:27 - Mental models
32:39 - Pause Tokens paper
37:09 - Examples of unhelpful mental models
40:04 - Solving a problem using prompting
41:57 - Prompting is like scaffolding
44:07 - Different prompt engineering tecnhiques
49:13 - Domain expertise is more valuable than writing skills
50:27 - Prompting resources


🔗 LINKS & RESOURCES
===============================
Artificial neural networks today are not conscious, according to Douglas Hofstadter - https://www.economist.com/by-invitati...
Learnprompting.org - https://learnprompting.org/
Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm - https://arxiv.org/abs/2102.07350
Think before you speak: Training Language Models With Pause Tokens - https://arxiv.org/abs/2310.02226

For a COMPLETE LIST of links and references, head over to https://twimlai.com/go/652.


📸 Camera: https://amzn.to/3TQ3zsg
🎙️Microphone: https://amzn.to/3t5zXeV
🚦Lights: https://amzn.to/3TQlX49
🎛️ Audio Interface: https://amzn.to/3TVFAIq
🎚️ Stream Deck: https://amzn.to/3zzm7F5