machine learning

Primus is an autonomous AI researcher that hypothesizes, reads papers, writes code, runs experiments on compute, and drafts research papers. The page shows example tasks, published-paper claims, waitlist access, and positioning for ML research workflows.

MLJAR Studio is a private AI data analysis workspace that runs locally, helps users explore data in natural language, generates and runs Python, automates machine learning experiments, and turns notebooks into shareable web apps.

Official implementation of LittleBit and LittleBit-2 for sub-1-bit LLM compression via latent factorization and quantization-aware training.

Clusy is an agent-native notebook platform for ML and data science that lets users describe a goal in plain language and have the system source data, set up experiments, run notebook cells, and return editable results in the cloud.

Open-source research skill that helps Claude, Codex, and OpenClaw run a more disciplined AI research workflow, from hypothesis and literature review through baselines, leakage checks, analysis, and paper writing.

A browser game experiment where bots are controlled by neural networks and evolved with a genetic algorithm. The 2026 update adds shared server-side evolution, improved bot behavior, and a PHP/SQLite backend.

An interactive explainer that teaches core AI and LLM evaluation metrics through playful visuals, including loss, perplexity, precision, recall, F1, accuracy, ROUGE, BLEU, and BERTScore.

Clusy is an agent-native notebook platform for ML and data science work in the cloud. The page says it can source data, inspect it, choose architecture and compute, and run end-to-end workflows, with a demo showing a finetuning task and follow-up work queued while the notebook runs.

An educational article explaining world models, latent states, dynamics learning, and planning for agents, with examples from gridworld, Dreamer, and MuZero.

A public slide deck about vLLM-compile, a project focused on bringing compiler optimizations to LLM inference and speeding up torch.compile for vLLM workflows.