Content I thought worth sharing. Some entries include my brief note.
An open-source MCP server that brings NVIDIA Auto Ontology’s semantic layer and a personal knowledge base to MCP clients such as Claude, ChatGPT, and Cursor. It supports database querying with ontology-checked SQL and ingestion of documents into structured, linked records with source references.
REA is a GitHub project providing an MCP interface for reverse engineering binaries, applications, and runtime behavior with agents. It is designed to help users understand how an example application works, down to the binary level.
This paper introduces ScientistTwo, a multi-agent framework intended to autonomously conduct scientific research from problem formulation through experimentation, ablation studies, and simulated peer review. It evaluates the system on tasks associated with ICLR, ICML, and NeurIPS papers, reporting automated generation of research papers and executable codebases.
AnyJev is an open-source GitHub project that uses a single LLM prefill to produce typed decisions and calibrated probabilities without generation, parsing, or fine-tuning. It includes methods for reducing answer-order sensitivity and improving calibration with a small number of labels.
A paper published in 2002, and very relevant now! One research direction is to to apply and evaluate learning theories, developed years ago, on AI agents.
This 2002 paper proposes a taxonomy for distinguishing near and far transfer of learning across knowledge domains, physical, temporal, functional, social, and modality contexts. It provides a framework for evaluating how learned skills, representations, and principles are applied in new situations.
An academic paper examining the emergence of large language model agents. The accompanying figure traces developments from early transformer architectures and language models to agent behaviors such as planning, negotiation, deception, and theory of mind.
The code is available here: https://github.com/SakanaAI/AI-Scientist
However, since it’s a bit old (compared to AI progress!), I guess it could be improved with claude code or codex.
A Nature paper associated with the AI Scientist research-automation project. From abstract: "We present The AI Scientist, which creates research ideas, writes code, runs experiments, plots and analyses data, writes the entire scientific manuscript, and performs its own peer review"
I send links, posts, podcasts, and the occasional meme to a small Telegram bot. It writes a one-line summary, files the item here, and the site rebuilds. My own comment, when I have one, appears in this box. Everything here is also in the RSS feed.
How the Notes section is fed and what the different parts of each entry mean.
This repo lets you to build an application based on an example (i.e., reverse engineering!). Thank you Cartez Dewberry for sharing this repo with me!