Summary In today's episode, I explain why you should prioritize context and prompts over model selection. Here's what this means for you. You will achieve much better results by focusing on the data you provide to the AI. You'll also learn these concepts: why model performance gaps are shrinking, how the Model Context Protocol connects…
Summary In today's episode, I explain the different levels of data safety companies face when using generative AI tools. Here's what this means for you. You can protect your organization's sensitive information by understanding the trade-offs between cost and privacy. You'll also learn these concepts: the varying tiers of AI security, how free tools compromise…
Summary In today's episode, I introduce the first foundational principle of generative AI. Here's what this means for you. You can master AI by applying it to every possible task until you discover its limits. You'll also learn these concepts: how to test AI across various workflows, how to manage data privacy risks, and why…
Summary In today's episode, I walk through the infrastructure and security steps you need to take to keep your data out of generative AI training pipelines, as part two of a five-part series. Here's what this means for you. You'll see how bringing critical services in-house puts a physical wall between your data and third-party…
Summary In today's episode, I explain why programmers should disclose when they copy code from GitHub or generate it with AI. Here's what this means for you. You gain a practical framework for protecting yourself legally and security-wise by documenting the lineage of every piece of code in your projects. You'll also learn these concepts:…
Summary In today's episode, I explain why bringing back the Gen X tradition of family passwords is essential for protecting against AI voice cloning scams. Here's what this means for you. You gain a simple authentication method that stops deepfake ransom calls from fooling you, your kids, your elderly parents, and even your coworkers. You'll…
Summary In today's episode, I break down a recent paper showing how easily attackers strip alignment from large language models like GPT-4 and Llama 2. Here's what this means for you. You need to understand that the safety guardrails on these models wear surprisingly thin, which matters enormously if you plan to deploy them in…
Summary In today's episode, I walk through how to prepare for universal analytics data migration as Google phases out the platform on July 1, 2023. Here's what this means for you. You gain a clear framework for deciding whether to back up your historical analytics data and which backup method fits your situation and skill…
