LLMs

Today I added an infinite-nonsense honeypot to my web site just to fuck with LLM scrapers, based on a "spicy autocomplete" program I wrote about 30 years ago. Well-behaved web crawlers will ignore it, but those "AI" people.... well, you know how they are. I'm intentionally not linking to the honeypot from here, for reasons, but I'll bet you can find it pretty easily (and without guessing ...

Local LLMs can evaluate 100s of result pairs a minute in a Macbook, enabling a new age of rapid search relevance improvements

I thought this was a fascinating post by Simon Willison: Things We Learned About LLMs in 2024 This increase in efficiency and reduction in price is my single favourite trend from 2024. I want the utility of LLMs at a fraction of the energy cost and it looks like that’

A LOT of LLMs

A lot has happened in the world of Large Language Models over the course of 2024. Here’s a review of things we figured out about the field in the past …

In How should you adopt LLMs?, we explore how a theoretical ride sharing company, Theoretical Ride Sharing, should adopt Large Language Models (LLMs). Part of that strategy’s diagnosis depends on understanding the expected evolution of the LLM ecosystem, which we’ve build a Wardley map to better explore. This map of the LLM space is interested in how product companies should address the proliferation of model providers such as Anthropic, Google and OpenAI, as well as the proliferation of LLM product patterns like agentic workflows, Retrieval Augmented Generation (RAG), and running evals to maintain performance as models change.

A look at why the batch paradigm is a relic of the past, how it hinders AI apps and why the future of AI demands a real-time event-streaming platform.

The Netscapes of AI

Small language models and local LLMs are increasingly popular with devs. We list the best models and provide tips for evaluation.

Vector databases are quite popular right now, especially for building recommendation systems, adding context to chatbots and LLMs, or comparing content based on similarity. In this guide, I'll explain what vector databases are, how they work, and when to use them.

No.333 — With AI, the future of Augmented Reality is in your ears ⊗ Why every company needs a futurist-in-residence ⊗ AI isn’t about unleashing our imaginations ⊗ Bringing life to L.A.’s infrastructure

How should software development respond to how LLMs operate? We need truly explainable Artificial Intelligence with testable components.

Got a modern Nvidia or AMD graphics card? Custom Llamas are only a few commands and a little data prep away

Best-in-class embeddings, rerankers, LLM-reader, web scraper, classifiers. The best search AI for multilingual and multimodal data.

No.329 — It feels like 2004 again ⊗ Three Future Frames ⊗ What is futures literacy ⊗ Cracks in LLMs’ “reasoning” capabilities ⊗ Trees and land absorbed almost no CO2 last year

Uber created a unified platform for serving large language models (LLMs) from external vendors and self-hosted ones and opted to mirror OpenAI API to help with internal adoption. GenAI Gateway provides a consistent and efficient interface and serves over 60 distinct LLM use cases across many areas.

A semantic router is a pattern that enables AI agents to choose the right LLM for the right task, while also reducing their LLM dependency.

Generative AI systems are prediction machines. This article breaks down neural networks and LLMs in nontechnical language.

Over the past few years, the evolution of AI-driven tools like GitHub’s Copilot and other large language models (LLMs) has promised to revolutionise programming. By leveraging deep learning, these tools can generate code, suggest solutions, and even troubleshoot issues in real-time, saving developers hours of work. While these tools have obvious benefits in terms of productivity, there’s a growing concern that they may also have unintended consequences on the quality and skillset of programmers.

Augmenting RAG with a knowledge graph that assists with retrieval can enable the system to dive deeper into data sets to provide detailed responses.

Predictability machines and personality

At Foundation for Economic Education (“The Ego vs. the Machine,” February 24), self-described “techno-optimist” Dylan Allman dismisses recent controversies over AI as a simple matter of wounded egos. “They feel, on some instinctual level, that if machines can do what they do — only better, faster, and more efficiently — then what value do they...

Dive into how Retrieval-Augmented Generation (RAG) can supercharge LLMs. Find out how RAG boosts LLM accuracy and get the scoop on the evolution and limitations of today's LLMs.

Setting up the Development EnvironmentBuilding the Graph RAG SystemIndexing Data in Neo4jImplementing Retrieval and GenerationCode Walkthrough and ExamplesDeploying and Scaling the Graph RAG SystemConclusion and Future Directions Graph RAG (Retrieval Augmented Generation) is an innovative technique that combines the power of knowledge graphs with large language models (LLMs) to enhance the retrieval and generation of

Introduction to Graph RAG Graph RAG (Retrieval-Augmented Generation) is a groundbreaking approach that combines the power of large language models (LLMs) with the structured knowledge representation of knowledge graphs. It addresses the limitations of traditional RAG techniques by leveraging the rich contextual information encoded in knowledge graphs, enabling more accurate and relevant search results. At

The AI community is embracing the sigmoid curve — that after initial rapid growth, progress starts to level off as we hit natural limitations.

Here’s the latest installment in the series on working with LLMS: For certain things, the LLM is a clear win. If I’m looking at an invalid blob of JSON that won’t even parse, there’s no reaso…

Thermometer, a new calibration technique tailored for large language models, can prevent LLMs from being overconfident or underconfident about their predictions. Developed at MIT and the MIT-IBM Watson AI Lab, it aims to help users know when a model should be trusted.

Ever wanted to raise millions of $ by adding "AI" to your company name; and you happen to want to...