All Episodes
The Prompt Desk — 52 episodes
What we learned about LLM’s in a year
Validating Inputs with LLMs
Why you can't automate everything with LLMs
Data Preparation Best Practices for Fine Tuning
Multilingual Prompting
Safely Executing LLM Code
How to Rescue AI Innovation at Big Companies
How UX Will Change With Integrated Advice
Prompting in Tool Results
Can custom chips save AI's power problem?
Towards an Inter-Agent Communication Standard
Should we let prompts write prompts?
The Bot Delusion
Experiments with the Networking Bot
Using Agents to Test Agents
MuIti Agent Engineering
Taming Erratic Behavior in AI Agents
[Bonus] LLMs making Web-Browsing Decisions
Mastering Chat Completions
[Bonus] Non-Engineers and Prompts
Measuring Business Results of LLMs with Abi Aryan
[Bonus] Next iteration of Chat Interfaces
GPT-4o - Do expectations meet reality?
[Bonus] Using Embedding Vectors
Breaking Down Tasks for AI Agents
How to protect your LLM against Prompt Injections
How do we know if Llama 3 is actually any better with Maxime Labonne
The Importance of Decomposition in Prompt Engineering
How LLM’s have changed MLOps with Andy McMahon
A Process for Prompt Experimentation
Prompt Injections to Coerce any LLM to do Anything You Want with Jonas Geiping
Is Your AI Really an Agent?
AI Agents in the Enterprise with Alan Wunsche
Programming 10x Faster with AI Augmentation
Prompt Design for AI Art with Sachin Kamath
Voodo in Prompt Engineering
Using LLMs to Generate Source Code: Part 2
LLM System Engineering with Denys Linkov
Why AI is NOT a competitive advantage
Prompt injection and LLM Security a Deep Dive with Peter Gostev
Why Small Language Models are Going to Eat the World
Data-free Quality Analysis of Deep Neural Nets with Charles H. Martin
Why AI Systems are More Complex than they Seem
How LLM-based Logic can Revolutionize Product Design
Natural Language APIs
Prompt Development Lifecycle: Part 1
Using LLMs to Generate Source Code: The First Step
Did OpenAI really just kill 1,000 Startups?
Sandwich Prompts: Instructions, Data, and Everything in Between
Prompt Size: Best Practices From Zero-Shot to Few-Shot Prompts
Decoupling for Clarity: The Future of Prompt-Based Development
Decoding LLM Quality: From Unit Testing to User Feedback