Published Sep 30, 2024

Interviewing Riley Goodside on the science of prompting

Delve into the transformative world of prompt engineering with Riley Goodside as he discusses the impact of ChatGPT, the evolving landscape of AI interactions, and the intricacies of model evaluation, offering insights into the challenges and future of AI prompting and communication.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

Interviewing Dean Ball on AI policy
Answers 383 questions
Interviewing Louis Castricato of Synth Labs and Eleuther AI on RLHF, Gemini Drama, DPO, founding Carper AI, preference data, reward models, and everything in between
Answers 383 questions
Interviewing Sebastian Raschka on the state of open LLMs, Llama 3.1, and AI education
Answers 383 questions
Interviewing Ross Taylor on LLM reasoning, Llama fine-tuning, Galactica, agents
Answers 383 questions
OpenAI chases Her
Answers 383 questions
Frontiers in synthetic data
Answers 383 questions
How to cultivate a high-signal AI feed
Answers 383 questions
Reverse engineering OpenAI's o1
Answers 383 questions
Text-to-video AI is already abundant
Answers 383 questions
AGI is what you want it to be
Answers 383 questions
Interviewing Tri Dao and Michael Poli of Together AI on the future of LLM architectures
Answers 383 questions
Google ships it: Gemma open LLMs and Gemini backlash
Answers 383 questions
A realistic path to robotic foundation models
Answers 383 questions
Alignment-as-a-Service: Scale AI vs. the new guys
Answers 383 questions
Name, image, and AI's likeness
Answers 383 questions

Dexa/Interconnects Audio

Interviewing Riley Goodside on the science of prompting

Topics covered

Popular Clips

Step by Step

Twitter's AI Dynamics

Evolving Evaluation Standards

Evolution of Prompt Engineering

Evaluation Challenges

Exploring Connections

Evaluating Model Inference

Model Behavior Insights

Prompt Engineering Insights

System Prompts Matter

Prompt Engineering Insights

AI's Real-World Impact

Model Specialization Insights

Evolving Search Dynamics

Episode Highlights

Evolution of Prompt Engineering

Future of AI Interaction

Prompting Challenges

AI Model Evaluation

Related Episodes

Interviewing Dean Ball on AI policy

Interviewing Louis Castricato of Synth Labs and Eleuther AI on RLHF, Gemini Drama, DPO, founding Carper AI, preference data, reward models, and everything in between

Interviewing Sebastian Raschka on the state of open LLMs, Llama 3.1, and AI education

Interviewing Ross Taylor on LLM reasoning, Llama fine-tuning, Galactica, agents

OpenAI chases Her

Frontiers in synthetic data

How to cultivate a high-signal AI feed

Reverse engineering OpenAI's o1

Text-to-video AI is already abundant

AGI is what you want it to be

Interviewing Tri Dao and Michael Poli of Together AI on the future of LLM architectures

Google ships it: Gemma open LLMs and Gemini backlash

A realistic path to robotic foundation models

Alignment-as-a-Service: Scale AI vs. the new guys

Name, image, and AI's likeness

Interviewing Riley Goodside on the science of prompting

Topics covered

Popular Clips

Episode Highlights

Evolution of Prompt EngineeringRiley Goodside, a leading prompting engineer, explores the transformative impact of ChatGPT on prompt engineering. He discusses the simplification of the process and the broader implications for AI model interactions.

Evolution of Prompt Engineering

Future of AI InteractionThe discussion shifts to the specialization of AI models and how this trend might shape future interactions. Riley Goodside and Nathan Lambert explore the evolving nature of prompting and its potential to transform user experiences with AI.

Future of AI Interaction

Prompting ChallengesRiley Goodside explores the technical challenges and misconceptions in AI prompting, emphasizing the need for clarity and effective evaluation methods. He shares insights on improving prompt communication and the potential impact of expertise in this field.

Prompting Challenges

AI Model EvaluationThe discussion shifts to the intricacies of evaluating AI models, focusing on the techniques, challenges, and the impact of system prompts. Riley Goodside and Nathan Lambert explore how these factors influence the reliability and fairness of model assessments.

AI Model Evaluation

Related Episodes