LLMs

Ash AI is a new extension for Ash Framework, enabling LLM integration for Elixir apps. Use Ash's declarative approach to take advantage of structured outputs, secure tool calling and to build MCP servers with ease.

The LLMs are here and they’ve already taken over large parts of the internet and of professional writing.

A deep dive into the novel Chain-of-Draft (CoD) Prompting that reducing LLM inference cost and latency like never before.

Just be careful not to shave off too many bits ... These things are known to hallucinate as it is

Your All-in-One Learning Portal: GeeksforGeeks is a comprehensive educational platform that empowers learners across domains-spanning computer science and programming, school education, upskilling, commerce, software tools, competitive exams, and more.

Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs. - brainlid/langchain

A New Software Development Lifecycle for LLMs

The landscape of Large Language Models (LLMs) is evolving rapidly, with powerful and open models being released at an unprecedented pace. As these technologies advance, so does the potential to integrate them into our existing systems. Traditionally, we've built systems with distinct layers such as the Application layer and Data Persistence layer.

LLMs and Vibe Coding are there. But why? Because our tech is not that advanced and we're disempowered by it. Make tech not suck, and you'll need no LLMs.

I finally use an LLM in an area where it's pretty good.

LLM scrapers are taking down FOSS projects' infrastructure, and it's getting worse.

Reviewing the capabilities and limitations of LLM agents in software development and their impact on skilled and less skilled developers.

Online discussions about using Large Language Models to help write code inevitably produce comments from developers who’s experiences have been disappointing. They often ask what they’re doing wrong—how come some …

Here comes the AI autumn, a season of change that will usher in a new chapter for these incredible technologies.

[Simon Willison] has put together a list of how, exactly, one goes about using a large language models (LLM) to help write code. If you have wondered just what the workflow and techniques look like…

Exploration of using mechanisms provided by Elixir/OTP to build LLM powered applications

Unstract is an open-source, no-code platform purpose-built for extracting data from unstructured documents using LLMs, with high accuracy. Easily deploy API and ETL pipelines for your unstructured data.

It's been just over two years and two months since ChatGPT launched, and in that time we've seen Large Language Models (LLMs) blossom from a novel concept into one of the most craven cons of the 21st century — a cynical bubble inflated by OpenAI CEO Sam Altman built to sell

Elixir, together with the Membrane framework, is great for building pipelines that enable seamless communication between users and LLMs.

DeepSeek (Chinese: 深度求索; pinyin: Shēndù Qiúsuǒ) is a series of open source Large Language Models (LLMs) from DeepSeek, an AI firm funded solely by Chinese hedge fund High-Flyer based in Hangzhou.

The release of DeepSeek R1 in January 2025 has created significant disruption in the LLM landscape, particularly in the realm of reasoning models. Here's a...

Quixotic is a nonsense generator designed to help static website operators confuse and confound bots and content-stealing LLM scrapers.

A reverse-proxy that serves diassociated-press style reimaginings of your upstream pages, poisoning any LLMs that scrape your content.

konterfAI is a model-poisoner for LLM (Large Language Models) to generate nonsense("bullshit") content suitable to degenerate these models.

Building Reliable LLM-powered Sofware in an Agentic World

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 …