The Rise and Fall of Jev(blog.alexewerlof.com)
49 points by flail | 34 comments
A Substack essay by Alex Ewerlöf critiquing the hype around Jev, a 'system one' decision model, and arguing AI progress since ChatGPT has been incremental.
#decision-models on Hacker News
13 stories tagged decision-models, newest first.
To Make, or to Buy: The Economics of Decision Models(pncnmnp.github.io)
49 points by pncnmnp | 2 comments
Blog post exploring the economics of decision models (choice, score, noul outputs) and forecasting whether to build or buy them, framed with Adam Smith.
Jev meets the Trolley Problem(zachlandes.com)
589 points by zlandes86 | 231 comments
Blog post by Zach Landes exploring how Jev, a fast cheap decision-making AI model that outputs choices with probabilities, handles the trolley problem.
Build your own decision model(nishtahir.com)
447 points by softwaredoug | 102 comments
Blog post by Nish Tahir explaining how to build a "system one" decision model that returns calibrated probabilities over allowed answers instead of structured LLM output.
Show HN: Jevman – AI decision models play Pac-Man(opper.ai)
60 points by felix089 | 11 comments
Opper's Jevman benchmark page where six AI decision models each played 100 Pac-Man games, with a leaderboard, replays, and a playable mode against model-controlled ghosts.
Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers(developers.redhat.com)
140 points by tomncooper | 50 comments
Red Hat Developer article benchmarking AI decision models like TypeSafe AI's Jev against LLM-as-a-judge and traditional classifier guardrails.
Clef: Open-weight decision models, and new RL fine-tuning platform(blog.cloudflare.com)
609 points by jasondavies | 213 comments
Cloudflare blog post announcing Clef, a family of open-source decision models, and a new reinforcement learning fine-tuning platform.
Jeeves. Reasoning improves Jev-like decision models(github.com)
232 points by nicowaltz | 89 comments
GitHub repository from PostHog for Jeeves, a project showing that reasoning improves Jev-like decision models.
Ollaya – Ollama for open-source, Jev-style decision models(ollaya.dev)
580 points by Ardakilic | 139 comments
Landing page for Ollaya, an open-source beta tool for running decision models locally to get calibrated typed answers about text or JSON.
Jev Is Not a Language Model, but It Breaks Like One(blog.checkpoint.com)
29 points by patresh | 5 comments
Check Point blog post on prompt injection attacks against Jev, a typed decision model that is not a language model but is still vulnerable to similar attacks.
Show HN: JevBench, a reproducible benchmark for typed decision models(benchmarkheaven.com)
119 points by florianstandhar | 32 comments
Benchmark Heaven's JevBench v1.3.0 leaderboard page ranking 52 Jev-class typed decision models on intelligence, calibration, speed and cost across 534 decisions.
Kev: Tiny Jev-like family of decision models built on top of Qwen3.5(github.com)
425 points by tosh | 192 comments
GitHub repository for Kev, a tiny Jev-like family of decision models built on Qwen3.5 that users can train and run themselves.
I built non-autoregressive decision models with RL a year ago(laya.convaiinnovations.com)
1270 points by nandakishor_ml | 304 comments
Blog post by ConvAI Innovations' founder describing Laya, an open-weight non-autoregressive decision engine trained with RL, and claiming priority over a frontier lab's similar work.