最新资讯
dev.to 你的 Agent Harness 应具备的 17 项能力 dev.to 离线 AI 记忆中 0.8 余弦阈值为何失效 dev.to Kimi K3.1 Pro 开放权重:自托管 2.8T 模型前的开发者清单 dev.to 如何通过工具调用引导模型以提升 Harness 质量 dev.to AI Agent 审计轨迹不等于对话记录 dev.to 精简 MCP server 工具数量:更少工具、更小影响面,双重收益 dev.to 为什么 git checkout 无法撤销 AI 编码 agent 的改动? wechat AI短剧门槛降降降!实测即梦短剧工作室:剧本分镜预演一条龙,伙伴计划长期护航 dev.to 让模型改写文档前,先量化事实保真度 dev.to 回放 153 个 Claude Code 与 Codex 会话,审计 Agent 的生产影响范围 dev.to 银行 77 意图分类最便宜 LLM:GPT-6.1 Terra 每次成功任务 $0.000727 theinformation.com Chesky的副业:Airbnb向CEO新设AI实验室出售IP
多元动态
登录 注册
大模型 www.aibase.com ·

TypeSafe AI 发布 Jev:不生成文本的 Transformer 模型,主打低成本决策

原文 我的收藏

TypeSafe AI 推出名为 Jev 的 Transformer 模型,不走 LLM 文本生成路线,而是输出概率并提供“校准决策”服务,面向软件自动化。创始人 Diogo Almeida 曾是 OpenAI 研究者并参与 RLHF 技术。Jev 不生成文本,输出 token 免费、输入按十亿 token 计费。开发者测试称,Vercel 用 Jev 替换 OpenAI 模型做命令安全分类,速度提升 5 至 18 倍且准确率更高;Bryo AI 测试中 Jev 准确率略低于 Gemini,但成本低 10 至 20 倍。

AI推荐理由 TypeSafe AI 由前 OpenAI 参与 RLHF 的研究者 Diogo Almeida 创立,发布不生成文本、只输出概率的 Transformer 模型 Jev,定位软件自动化中的低成本决策与校准输出,避开 LLM 的幻觉与冗余生成成本。文中给出开发者测试:Vercel 用 Jev 替换 OpenAI 模型做命令安全分类,速度提升 5 至 18 倍且准确率更高;Bryo AI 测试中 Jev 准确率略低于 Gemini,但成本低 10 至 20 倍。新信息在于非生成式 Transformer 的定价与决策场景,局限是来源为 AIbase 转述、缺少论文或官方基准,测试数据为开发者自述,需谨慎看待。

72

正文

TypeSafe AI Launches Jev: A Transformer Model That Does Not Generate Text, Focused on Low-Cost Decision Making AIbase基地 Published inAI News · 2 min read · Sep 20, 2026 3 TypeSafe AI has released a new Transformer model called Jev, attempting to bypass the text generation paradigm of large language models (LLMs), offering probabilistic outputs and "calibrated decision" services for software automation. Diogo Almeida, a former researcher at OpenAI and participant in RLHF technology, founded TypeSafe AI two years ago after leaving OpenAI. He believes that optimizing models around human language is not suitable for computer automation scenarios. Jev does not generate text but instead outputs probabilities, thus avoiding the hallucination and redundant generation costs of traditional LLMs. Its output tokens are free, while input is billed by the billion tokens. Developer tests show that Vercel improved speed 5 to 18 times and achieved higher accuracy by replacing OpenAI models with Jev for command security classification; in Bryo AI's test, Jev's accuracy was slightly lower than Gemini, but the cost was 10 to 20 times lower. This article is from AIbase Daily Scan to view Welcome to the [AI Daily] column! This is your daily guide to exploring the world of artificial intelligence. Every day, we present you with hot topics in the AI field, focusing on developers, helping you understand technical trends, and learning about innovative AI product applications. —— Created by the AIbase Daily Team © Copyright AIbase Base 2024, Click to View Source -

来源报道 · 1 篇 · 以下链接均前往原始媒体

← 返回精选动态 原文

更多内容