LLMs

How to parse content from a tool that is made to speak in human sentences.

The Instructor Elixir library lets you retrieve structured output from LLMs like the OpenAI GPT models.

Understanding vectors, tokens and embeddings is fundamental to grokking how large language models process language.

These are the main potential bottlenecks that negatively impact the performance of RAG pipelines targeting production LLM environments.

We dig into the technology behind Perplexity’s Copilot, which was inspired by the FreshLLMs paper that proposed search engine-augmented LLMs.

The path toward hands-on autonomous learning is through large language models (LLMs). Jon Udell shows how the EdTech sector can use AI.

It seems that each week brings a dozen new generative AI-based tools and services. Many are wrappers to ChatGPT (or the underlying LLMs such as GPT 3.5 Turbo), while some bring much more. Ollama is one of the latter, and it's amazing. In this blog post, I'll briefly examine

AI will improve in accuracy, creativity and speed. Even LLMs. But there seems to be an inherent tradeoff between these attributes, so that you can’t optimize more than two of them at once. To be clear, we will have AIs … Continue reading →

Find, download, and experiment with local LLMs

More efficient matrix multiplication algorithms could save millions of dollars on computationally intense tasks such as training LLMs.

I saw this post over on json.blog, OpenAI Is Just Uber, which sounds like it makes sense, but I think is drawing the wrong conclusions on a couple fronts. A decade later, ride-sharing hasn’t evolved significantly since its launch. Costs have risen as consumers now pay the actual

TL;DR Context Writing A 1996 Essay Again in 2023, This Time With Lots More Transistors ChatGPT 3 Gathering the Sources PrivateGPT Ollama (and Llama2:70b) Hallucinations What I Learned TL;DR I used …

It's been a big year for Large Language Models. For developers, the impact of LLMs has been largely felt in AI dev tools and assistants.

Retrieval-augmented generation (RAG) is a cutting-edge approach in NLP and AI. Badrul Sarwar, a machine learning scientist, shares his tips.

Both OpenAI and Google have released guidance for website owners who do not want the two companies using the content of their sites to train the company's large language models (LLMs). We've long been supporters of the right to scrape websites—the process of using a computer to load and read pages...

As well as the proliferation of LLMs, there has been an expansion of dev tools for AI. We look at five key trends this year in AI development.

Prompt engineering technique helps large language models (LLMs) handle pronouns and other complex coreferences in retrieval augmented generation (RAG) systems.

tl;dr: OpenAI leaked AI breakthrough called Q*, acing grade-school math. It is hypothesized combination of Q-learning and A*. It was then refuted. De…

It allows a user to be served with a personalized adapter while enhancing the LLM's response by adding recent data as context.

Humane finally actually announced their first product: Ai Pin. Here's their introduction video. I love technology, and I think I'm generally enthusiastic about new tech that pushes things forwards. I'm enthusiastic about the ways LLMs are creating so many new things that weren't even possible literally one year ago, and

First we fixed a bug in an SQL query. Then we rethought the design of the query. Here are further ways to use LLMs to adjust your SQL queries.

How the tech news aggregator daily.dev created an AI search, including using an LLM Gateway to streamline and optimize interactions with LLMs.

Here’s number 12 in the series on LLM-assisted coding over at The New Stack: Let’s Talk: Conversational Software Development I keep coming back to the theme of the first article in this serie…

Here’s everything you need to know to build your first LLM app and problem spaces you can start exploring today.