- wöchentlichErscheinungsrhythmus
- 19 mintypische Länge
- 2. Okt. 2024letzte Folge
Folgenzu den neuesten
Prompt Injections to Coerce any LLM to do Anything You Want with Jonas Geiping
Prompt Injections might be the single biggest risk to the deployment of LLM systems. In this episode of The Prompt Desk, your host Bradley Arsenault sits down with researcher Jonas Geiping to talk about his research on LLM security. Jonas a
Is Your AI Really an Agent?
Explore the six essential components that define an AI agent in 2024, including input/output, memory, loops and recursion, third-party actions, and comprehension. Join Brad and Justin as they discuss the criteria needed for a sophisticated
AI Agents in the Enterprise with Alan Wunsche
Are you wondering how LLM Agents can be applied in large enterprises? Are we all going to become managers to teams of AI systems, cobbled together like a rag-tag group of robot butlers? In the latest episode of The Prompt Desk, hosts Justin
Programming 10x Faster with AI Augmentation
In this episode of The Prompt Desk, hosts Justin Macorin and Bradley Arsenault discuss the various ways they have been using coding assistants, such as Github Copilot, in order to boost their productivity as software developers. The two exc
Prompt Design for AI Art with Sachin Kamath
Join us with Sachin Kamath as we explore how to use AI in creative projects effectively and how we may effectively integrate AI into existing workflows, significantly enhancing productivity and creative output. We discuss frameworks for adv
Voodo in Prompt Engineering
Does Voodo in prompt engineering exist? The evolution from manual prompt crafting to automated refinement and optimization in AI interactions marks a transition from art to science. Let's discuss how initial natural language inputs transfor
Using LLMs to Generate Source Code: Part 2
This episode discusses improving code generation with LLMs by dynamically extracting functions and context, using techniques like Python's inspect modules and JavaScript's toString. The goal is to produce code that integrates well with exis
LLM System Engineering with Denys Linkov
Join us as we explore the advancements and challenges in implementing Retriever-Augmented Generation (RAG) systems for document retrieval and summarization, examining selective information inclusion, re-ranking strategies, and the importanc
Why AI is NOT a competitive advantage
Don't miss out on our discussion about the critical factors of expert domain knowledge, intellectual property, and the impact of first-mover advantage. These factors remain the most important competitive advantages, even in today's rapidly
Prompt injection and LLM Security a Deep Dive with Peter Gostev
In today's world, application security is more important than ever before. One of the most significant risks to application security is prompt injection. It can cause irreparable damage to your business. That's why it's critical to understa
Why Small Language Models are Going to Eat the World
Let's discover the rise of local Small Language Models (SLMs), contrasting them with their larger, internet-dependent counterparts - LLMs. We discuss real-world applications like Google Maps, in-browser neural networks, and Apple Photos, ex
Data-free Quality Analysis of Deep Neural Nets with Charles H. Martin
In this episode, we interview Charles H Martin about his open-source Weight Watcher project ( found here https://weightwatcher.ai/ ), which provides ways to test the quality and fit of deep neural networks without having to rely upon a vali
Why AI Systems are More Complex than they Seem
Artificial Intelligence (AI) systems are often considered magical, but they are actually composed of several components, with LLMs being only one of them. It is essential to understand that AI systems utilize a range of components, includin
How LLM-based Logic can Revolutionize Product Design
Conditional logic powered by Large Language Models (LLMs) is transforming the traditional if/else statements in software applications, enabling quicker and more efficient integration of AI-based conditional logic. This advancement significa
Natural Language APIs
Should computers talk English to eachother? This podcasts discusses how computers can use natural language queries to execute API and database calls. Join us as we discuss the challenges, opportunities, and future potential of natural langu
Prompt Development Lifecycle: Part 1
Dive deep into the world of prompt development where we break down the different steps of developing prompt-based applications. From your first prompt to a fine-tuned version, we unravel the intricacies of prompt engineering, exploring how
Using LLMs to Generate Source Code: The First Step
Dive deep into the world of using Large Language Models (LLMs) to generate source code as we explore the importance of types and schema definitions. Join us as we discuss the challenges of generating accurate and reliable code, the role of
Did OpenAI really just kill 1,000 Startups?
Dive deep into OpenAI's newest press release as we discuss and examine the implications of their newest features, and draw parallels with past tech giants like AOL, Netscape, and Apple's Flashlight application. Join us for a thought-provoki
Sandwich Prompts: Instructions, Data, and Everything in Between
Dive deep into how instruction and data placement can have a significant impact on prompt and output quality. Join us as we explore how we use statistics to measure prompt quality and what data and instruction placements yield the best succ
Prompt Size: Best Practices From Zero-Shot to Few-Shot Prompts
Dive deep into the art of prompt engineering as Brad and Justin share their personal experiences with machine learning models, unravel the mysteries of why shorter prompts often yield better results and the nuances of zero-shot vs. few-shot
Decoupling for Clarity: The Future of Prompt-Based Development
Dive into the world of prompt deleveopment best practices as we explore the importance of decoupling prompts from source code. Learn about the challenges of hard-coding, the rising trends in the realm of prompts engineering, and how proper
Decoding LLM Quality: From Unit Testing to User Feedback
Dive deep into the nuances of measuring the quality of Large Language Model (LLM) prompts, as we explore past methodologies, and evaluate both qualitative assessments and large-scale testing techniques. Join us as we discuss the challenges
