@neural_avb: Simply DSPy code to generate choice-based JEV decision training data from any raw text source Some of the newer models …
Summary
This article describes using DSPy code to generate choice-based JEV decision training data from raw text, highlighting the cost-effectiveness with cheap models like gpt-6-luna and deepseek-v4.1-flash.
View Cached Full Text
Cached at: 09/23/26, 04:13 PM
Simply DSPy code to generate choice-based JEV decision training data from any raw text source
Some of the newer models like gpt-6-luna, deepseek-v4.1-flash etc are so cheap right now that you can pretty much produce 50K high quality examples in ~5-10$ https://t.co/1PZTQ0uQDr
Similar Articles
@_avichawla: https://x.com/_avichawla/status/2101563610644496464
The article explains how to build a local decision engine using open-source LLMs and SGLang, enabling efficient scoring and probability distributions for fixed choices without full text generation, compared to systems like Jev.
I open sourced 12M agentic decision examples for training Jev style models
The author has open-sourced Jev Decisions v1, a dataset of 12 million examples for training AI models on agentic decisions like tool selection and routing, to address data gaps in agent decision-making.
@neural_avb: https://x.com/neural_avb/status/2072294078805684613
This paper introduces Autodata, a method that uses an agentic 'data scientist' AI to automate the creation of high-quality synthetic datasets through iterative generation, verification, and refinement, specifically optimized for reinforcement learning (GRPO) to improve reasoning in language models.
Reverse-engineered Jev-like model
The article describes 'jevlike', a reverse-engineered AI model for selecting among text options in one pass, with demos on games like Doom and chess, hosted on GitHub.
Been experimenting with Jev — interesting approach to AI agents
The author discusses experimenting with Jev, a tool for AI agents focused on decision-making, which claims significant speed and cost benefits compared to using large language models for all tasks.