search
decision model
Trends
- 1
A new guide walks through building your own decision model, explaining how to structure the choices, weights and outcomes that drive automated decisions. The piece focuses on doing it from scratch rather than relying on packaged machine learning tools, and it is drawing attention from software engineers and data practitioners discussing how practical and transparent hand-built models can be compared with off-the-shelf approaches.
- 2Apple blocks removal of AI models in macOS 27●Tell HN: Apple not letting removal of AI models on macOS 27 is outrageous
Apple is preventing users from removing built-in AI models in macOS 27, according to a complaint gaining traction on Hacker News. The poster calls the decision outrageous, arguing users should retain control over preinstalled AI software on their own machines. The discussion has drawn dozens of upvotes, with the apparent friction being Apple's push to embed AI deeply into its operating system.
- 3
OpenAI has opened its Decisions API to public beta, letting developers build applications that return structured decision outputs rather than free-form text. The announcement is drawing attention on developer forums, where commenters are weighing potential use cases for automated recommendation and choice-making systems, as well as questions about reliability, pricing and how the API compares with existing model endpoints.
- 4
A new benchmark called Jevman tests AI decision-making models by having them play Pac-Man, and it was shared on Hacker News where it drew attention from the community. The project, hosted by Opper.ai, offers a playful but practical way to compare how well different AI models handle sequential decisions under uncertainty.
Repos
- trycua/cua Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data gene
- firelex/jeff Millisecond decisions, any domain: a 0.8B open "System 1" model that picks between your options with calibrate
- angel291592/Intent-Router Intent compiler for AI agents — converges vague requests into typed IntentSpec contracts (probe, ask, or halt before rou
- nokia-applied-research/AnyJev Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welc
- ollaya-dev/ollaya Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollam
- extend-hq/jevbox
- Contrastive-LM/CLM
- Liuziyu77/Valen Train a Jev-like multimodal model by yourself. System One Model, now with vision.
- kydlikebtc/awesome-jev 1207 public resources for Jev, TypeSafe AI's System One decision model, indexed by decision pattern. Source citatio
- Rizzo-AI-Academy/rizzo-flow The open, local take on Jev: typed decisions from an LLM, without generating a single token
- jev-chat/jev-chat-jarvis The chat decision assistant: before you reply, Jev reads the chat, judges intent and risk, and drafts replies you fill i