On this episode: Stack Overflow senior data scientist Michael Geden tells Ryan and Ben about how data scientists evaluate large language models (LLMs) and their output. They cover the challenges involved in evaluating LLMs, how LLMs are being used to evaluate other LLMs, the importance of data validating, the need for human raters, and more needs and tradeoffs involved in selecting and fine-tuning LLMs.
In the wake of the XZ backdoor, Ben and Ryan unpack the security implications of relying on open-source software projects maintained by small teams. They also discuss the open-source nature of Linux, the high cost of education in the US, the value of open-source contributions for job seekers, and what Apple is up to AI-wise.
This new LLM technique has started improving the results of models without additional training.
The home team is joined by Michael Foree, Stack Overflow’s director of data science and data platform, and occasional cohost Cassidy Williams, CTO at Contenda, for a conversation about long context windows, retrieval-augmented generation, and how Databricks’ new open LLM could change the game for developers. Plus: How will FTX co-founder Sam Bankman-Fried’s sentence of 25 years in prison reverberate in the blockchain and crypto spaces?
The home team discusses the challenges (hardware and otherwise) of building AI models at scale, why major players like Meta are open-sourcing their AI projects, what Apple’s recent changes mean for developers in the EU, and Perplexity AI’s new approach to search.
Machine learning scientist, author, and LLM developer Maxime Labonne talks with Ben and Ryan about his role as lead machine learning scientist, his contributions to the open-source community, the value of retrieval-augmented generation (RAG), and the process of fine-tuning and unfreezing layers in LLMs. The team talks through various challenges and considerations in implementing GenAI, from data quality to integration.
On this episode: Roie Schwaber-Cohen, Staff Developer Advocate at Pinecone, joins Ben and Ryan to break down what retrieval-augmented generation (RAG) is and why the concept is central to the AI conversation. This is part one of our conversation, so tune in next time for the thrilling conclusion.
If you’re building experimental GenAI features that haven’t proven their product market fit, you don’t want to commit to a model that runs up costs without a return on that investment.
Intuit shares what they've learned building multiple LLMs for their generative AI operating system.
Ben and Ryan discuss how complex images (and maybe even interactive games) are being encoded in living cells, the latest trends in prompt engineering, and the educational benefits of gaming.
Why replacing programmers with AI won’t be so easy.
While there’s a lot of dangers out there, it’s not all doom and gloom; we also talk about how to mitigate these threats.
Ben and Ryan discuss the golden age of digital piracy, the Sisyphean task of keeping kids off the internet, and seasonal depression in AI.
The home team talks about Google’s new AI model, Gemini; the problems with regulating technology that evolves as quickly as AI; how governments can spy on their citizens via push notification; and more.
Ben and Ryan discuss how LLMs are changing the industry and practice of software engineering, a notorious Crash Bandicoot bug, and communication via series of tubes.
Ben, Ryan, and Eira convene to discuss return-to-office mandates, what’s surprising about employee attrition in 2023, and how technology can preserve digital records of cultural heritage sites before they’re lost for good.
We chat with IBM about how their watsonx platform makes generative AI more than just a fun toy.
The core challenge posed by generative AI right now is that unlike conventional applications, LLMs have no “delete” button.
Retrieval augmented generation (RAG) is a strategy that helps address both LLM hallucinations and out-of-date training data.
Ben and Ryan settle in for a wide-ranging discussion about whether large language models know anything, whether language ability is unique to humans, and what the end of the Hollywood writers’ strike says about the future of AI-generated content.
A Qualcomm expert breaks down some of the tools and techniques they use to fit GenAI models on a smartphone.
Ben and senior software engineer Kyle Mitofsky are joined by two people who worked on the launch of Overflow AI: director of data science and data platform Michael Foree and senior software developer Alex Warren. They talk about how and why Stack Overflow launched semantic search, how to ensure a knowledge base is trustworthy, and why user prompts can make LLMs vulnerable to exploits.
Knowledge management and AI, VPN security, and an SVG deep dive.
Large language models seem to possess the ability to reason intelligently, but does that mean they actually know things?
