Hemmingway-1 is a 27-billion-parameter open-weight AI model optimized for everyday writing tasks like emails and messages. It outperformed larger models including GPT-6 Astra and Fable 5.1 in blind evaluations, scoring 26 points higher than competitors on human-likeness and excelling at practical writing requests like financial and administrative correspondence.
Thomson-1.0-Small is an open-weight frontier foundation model developed by Thomson Reuters using continual learning on the Qwen3.6-35B base model. It achieves high performance across legal, tax, and journalism domains through constitutional value alignment, data-centric training on 19T+ tokens, and agentic deep research capabilities, demonstrating that frontier model performance is achievable by institutions beyond heavily funded players.
Mini-AGI is a continual learning language model that trains from scratch on 8GB VRAM by storing weights on disk and paging them as needed. It learns continuously from a data stream without catastrophic forgetting, enabling users to train and own their own models on consumer hardware.
jevchat turns Jev (an API) into a chatbot by repeatedly asking which symbol comes next given user input and reply-so-far, sampling from Jev's probability distributions over alphabets. The project offers multiple sampling strategies (choice, bisect, buckets, refine) and alphabets, with interactive chat and command-line modes for experimental use.
A developer tested TypeSafe's Jev, a text-only language model, on a drawing-guessing task by converting doodles into SVG coordinates and base64-encoded images. Using 400 drawings from Google's Quick, Draw! dataset across ten object categories, they evaluated how well Jev could classify sketches despite being designed for text input only.