More than two years into the AI hype, here’s a grounded overview of this period from the perspective of a regular software developer.

Learn how to make unreliable AI APIs reliable using proven distributed systems patterns. Real example: reduced LLM costs from $20 to $0 with transactional outbox.

Random thoughts, articles and projects by a chronic overengineer.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Continue enables you to easily create your own coding assistant directly inside Visual Studio Code and JetBrains with open-source LLMs.

There’s a lot of excitement about what AI (specifically the latest wave of LLM-anchored AI) can do, and how AI-first companies are different from the prior generations of companies. There are a lot of important and real opportunities at hand, but I find that many of these conversations occur at such an abstract altitude that they border on meaningless. Sort of like saying that your company could be much better if you merely adopted more software. That’s certainly true, but it’s not a particularly helpful claim.

On the ProjectVRM list, John Wunderlich shared a find that makes clear how advanced and widespread  AI-based shopping recommendation has gone so far (and not just with ChatGPT and Amazon). Here it is: Envisioning Recommendations on an LLM-Based Agent Platform: Can LLM-based agents take recommender systems to the next level? It's by Jizhi Zhang, Keqin Bao, Wenjie…

 This study explores the neural and behavioral consequences of LLM-assisted essay writing. Participants were divided into three groups: LLM, Search Engine…

Playing Minesweeper with Augmented Reasoning

Meet Clara – your private, on-device AI assistant & agent builder. Complete AI development suite with LumaUI, ComfyUI, N8N automation, and local LLMs. No cloud, no data sharing.

My smartest friends have bananas arguments about LLM coding.

LLM “reasoning” is so cooked they turned my name into a verb

Important new study from Apple

A solo D&D experiment turned into a lesson in building agentic AI apps, connecting LLM prompt tuning, Model Context Protocol and Spring AI.

How the Elixir community can survive — and thrive — in an age of LLMs.

Introduction With the rise of "vibe-coding," it's easy to forget that LLMs offer much more than just code generation. Their real strength lies in language.

The hype about the potentials (it’s always future potential, never real current use) of AI has discarded its last cycle (“reasoning models”/”deep research”, both terms being factually untrue and deeply deceiving at best) and moved to a new double whammy of “agentic AI” and “Vibe Coding”. Now “agentic AI” basically just means that some LLM […]

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.