A storage that can be used to keep memory across sections.

This claims an innovative “holographic memory” that is apparently more compact and requires less infrastructure than RAG.

An in-depth article about working with LLMs from a senior engineering perspective.

Convert PDF to markdown JSON quickly with high accuracy - datalab-to/marker

A tool that gives more context to agent, based on a curated set of API documentation.

via: https://news.ycombinator.com/item?id=47317132

Human DX optimizes for discoverability. Agent DX optimizes for predictability. What I learned building a CLI for agents first.

An LLM benchmark testing the model’s push back (or lack thereof) against BS.

Interactive AI timeline tracking 194 Large Language Models from 2017 to 2026. Explore the history of ChatGPT, GPT-4, Claude, Gemini, LLaMA, Mistral, DeepSeek and every major LLM ever released.

via: https://news.ycombinator.com/item?id=47019133

via: https://news.ycombinator.com/item?id=47000034

The research-plan-implement workflow I use to build software with Claude Code, and why I never let it write code until I’ve approved a written plan.

Aria on the language of certain FOSS spaces and it’s relationship to llms.

article about the shortcomings of LLMs in “adversarial” contexts