Jev发布帖
Diogo Almeida介绍了Jev,即TypeSafe的结构化决策模型。观看发布影片,并探索原始帖子了解该模型的方法、示例和作者报告的性能。
Latest addition
Source check
Recent activityDiogo Almeida介绍了Jev,即TypeSafe的结构化决策模型。观看发布影片,并探索原始帖子了解该模型的方法、示例和作者报告的性能。
TypeSafe的正式发布公告介绍了实验室,并引导开发者使用Jev。公告包含Diogo Almeida的发布影片和原始介绍。
TypeSafe宣布Jev向公众开放,无需等待列表。官方控制台是将类型化决策应用于自己应用程序的起点。
TypeSafe强调Jev的类型化输出方法:应用程序提供状态和问题,然后根据概率、选择或评分进行操作。相关公告还介绍了Venice API集成。
Start with the Launch Post. Explore four official signals.
15 项资源
AI-assisted summaries and translations. Check original sources for context and performance claims.
A developer project offering a Chrome extension to blur low-value LinkedIn posts, collected for the creative shelf.
JEVLAB ARTSource-linked curation
A tool enhancing zsh autosuggestions with Jev-based ranking instead of prefix matching.
JEVLAB ARTSource-linked curation
Visual-Jev is a GitHub research project that makes decisions based on images rather than text descriptions of visual content.
Source-linked curation
Mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.
Source-linked curation
Can a System One model steer music? Jev picks the plan (enums only); code renders sheet, audio and MIDI.
JEVLAB ARTSource-linked curation
Semantic GitHub PR labels using Jev's typed decisions, with conceptual scope instead of line counts.
JEVLAB ARTSource-linked curation
Claude Code plugin that scores review findings, debug hypotheses and design options with TypeSafe's Jev — calibrated probabilities instead of one more opinion.
Source-linked curation
A GitHub project developing a screen overlay to identify manipulative interface patterns.
Source-linked curation
A developer project using Jev to score sales calls, collected for the creative shelf.
Source-linked curation
A SillyTavern extension that evaluates replies before they are displayed, collected for the creative shelf.
Source-linked curation
A tool that analyzes WeChat threads for emotion, intent, and reply quality.
Source-linked curation
Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon.
Source-linked curation
Fork of OpenPoke where the yes/no decisions go to Jev instead of Claude Sonnet, with a same-inputs A/B against the replaced LLM decision and a 43,776-request adversarial run on the injection gate.
Source-linked curation
Go client for TypeSafe's System One API and its model Jev: typed judgments and calibrated probabilities instead of generated text.
Source-linked curation
Put a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit.
Source-linked curation