A developer named Antelo has published ldraw-nova, an open-source tool that lets an AI agent take a user's model idea and build it into a LEGO design using the LDraw format. The output includes source code, a Blender-editable glTF file, multiple viewing options including a VR mode for Meta Quest 3, and a log of the agent's chat and reasoning process. The project is distributed via Docker and relies on a companion semantic search tool called jev-rerank, built by the same author, to help agents find matching parts and reference models.
github.com
· 2026-10-02
TypeSafe AI released an AI model called Jev about three weeks ago. The model has already prompted other developers to create copycat versions and has stirred discussion in Silicon Valley about alternatives to large language models.
wsj.com
· 2026-10-02
A researcher evaluated Jev, TypeSafe's 'System One' classifier model built by attaching a classification head to a pretrained transformer, to see how well its output probability distributions match known physical answers. The test used questions with mathematically established solutions, such as the Maxwell-Boltzmann velocity distribution for a particle in thermodynamic equilibrium, comparing Jev's predicted probabilities against the known correct distributions. The author notes the entire experiment series cost less than $4.00 to run.
maximumeffort.substack.com
· 2026-10-02
Cloudflare has released two open-weight models, Clef and Clef-flash, built for structured decision tasks like yes/no answers, multiple-choice, and ranking. The models use frozen, post-trained versions of Qwen backbones, support images, video, and a 64K context window, and are downloadable via Hugging Face.
tech.slashdot.org
· 2026-10-01
Cloudflare has launched Clef and Clef-flash, two decision models hosted on Workers AI and compatible with the Jev API. The company says Clef currently leads the Jev Decision Index benchmark, and both models are open-sourced on Hugging Face under an Apache 2.0 license. Cloudflare also introduced a reinforcement learning product that lets customers fine-tune Clef for their own use cases.
blog.cloudflare.com
· 2026-10-01
At OpenAI's Dev Day, CEO Sam Altman introduced a new 'Decisions API' that lets developers give the company's Luna model a predefined set of options to choose from, such as image categories or agent behaviors, returning fast, low-cost outputs. The tool appears similar to Jev, a classifier model released earlier this month by TypeSafe AI for software automation tasks. OpenAI's API is currently in limited preview, and TypeSafe did not respond to requests for comment on the similarities.
techcrunch.com
· 2026-09-30
TypeSafe AI has released Jev, a model designed to convert natural-language input and application state directly into typed decisions, returning choices, scores and probabilities as JSON. The company says Jev uses a new architecture, a parallel sampler, and a training method called Reinforcement Learning for Calibrated Decisions to generate probabilities without token-by-token generation. TypeSafe reports significant speed and cost improvements over general-purpose LLMs for decision-making workflows.
columnar.tech
· 2026-09-29
A technical writeup examines the recently released Jev AI model, which specializes in text classification and has generated significant buzz in technical communities. The author, who has no affiliation with Jev, traces the evolution of classification methods from early bag-of-words approaches to modern large language models, situating Jev within that history to explain its design and appeal.
magazine.sebastianraschka.com
· 2026-09-29
Andrew Boyd, founder of Standard Agents Inc., says his Jev decision model beat Pokémon Red's Elite Four and Champion, reaching the Hall of Fame on September 23, 2026, less than a week after the run began. Jev isn't a chatbot or LLM; it picks from lists of weighted options rather than reading the screen, while Anthropic's Claude Opus 5 monitored the game log and adjusted those options to help it when stuck. A harness changelog logged 474 fixes, including repeated failures like walking into a shut door 53 times and looping a ladder 124 times.
tomshardware.com
· 2026-09-27
A technical post describes a method for turning an off-the-shelf large language model, GLM-5.3-Flash running on Privatemode, into a decision-making model that outputs a typed choice with confidence scores in a single forward pass, rather than generating a full JSON response. Benchmarked against public datasets, the setup reportedly matches TypeSafe's specialized Jev model in decision accuracy and speed, while also supporting typed decisions on images, which Jev cannot do.
privatemode.ai
· 2026-09-26
Ollaya is a new local server for running open-source 'decision models' like Laya, gliclass and NLI, designed to answer structured questions in a single forward pass rather than generating text token by token. It implements the same /v1/systemone and /v1/models endpoints as TypeSafe's hosted API, so the official TypeSafe Python SDK can point at a local Ollaya server without code changes.
ollaya.dev
· 2026-09-25
A Show HN submission introduces 'Doom or Bloom,' a web tool that asks users a series of questions to plot their views on AI's future along two axes: civilizational versus incremental change, and outcomes ranging from doom to bloom. The site also displays example results from simulated users and lets visitors explore how others' responses are plotted.
doom-or-bloom.com
· 2026-09-25
GoKawiil