AI UP LAB面向任务的 AI 实践资源AI resources for real tasks
收藏Saved
更多More
StarStar
TypeSafe AI TypeSafe AI 官方 Official 社区 showcase Community showcase + 精选 + Featured

Jev / System One Models（TypeSafe AI） Jev / System One Models (TypeSafe AI)

Jev / System One Models (TypeSafe AI)

TypeSafe AI 于 2026-09-15 发布的首个公开 System One Model。面向软件内决策而非聊天：输入非结构化状态，输出类型安全的结构化决策，并附带校准概率与置信度。官方称新架构 + 并行采样 + Reinforcement Learning for Calibrated Decisions（RLCD）；目前为早期访问；速度、价格与评测倍率均为厂商自述，本库未复跑其工作流评测。 TypeSafe AI’s first public System One Model, announced 2026-09-15. Built for in-software decisions rather than chat: unstructured state in, type-safe structured decisions out with calibrated probabilities and confidence. Vendor claims a new architecture, parallel sampling, and Reinforcement Learning for Calibrated Decisions (RLCD); currently early access; speed, pricing, and eval multipliers are all vendor claims, and the workflow evals were not re-run by this library.

来源Sources

官方模型页 Official model page TypeSafe：Introducing System One Models & Jev TypeSafe: Introducing System One Models & Jev TypeSafe AI 2026年9月15日 Sep 15, 2026 https://typesafe.ai/blog/introducing-system-one-models-and-jev 官方模型页 Official model page TypeSafe AI 官网 TypeSafe AI homepage TypeSafe AI 2026年9月15日 Sep 15, 2026 https://typesafe.ai/ 社区 showcase Community showcase Hacker News：Introducing System One Models and Jev Hacker News: Introducing System One Models and Jev Hacker News 2026年9月15日 Sep 15, 2026 https://news.ycombinator.com/item?id=49717558

为什么推荐Why we recommend it 收录理由：9/15 新一类 frontier 决策模型公告，HN 热议，适合 Models 看板。边界：速度 / 成本 / 评测倍率均为厂商自述（取自官方博文与官网），本库未独立核实；早期访问，本库未实测 API。三条来源 URL 于 2026-09-16 核到 200。无预览图。 Why: a 9/15 announcement of a new class of frontier decision model with strong HN interest; fits the Models board. Boundary: speed / cost / eval multipliers are vendor claims taken from the official blog post and homepage, not independently verified here; early access, API not tested by this library. All three source URLs returned 200 on 2026-09-16. No preview image.

要点（官方称 / 社区称）Highlights (vendor / community claims)

  • 官方称：面向 automation 的 System One 模型类——结构化输出、类型不出错、每次回答带校准置信度；不做字符串生成。 Vendor claim: a System One model class for automation — structured outputs, no type errors, calibrated confidence on every answer; not string generation.
  • 官方称：端到端约 70ms–500ms；输入约 $0.042 / MTok，输出免费计量；工作流评测上相对前沿 LLM 可达约 193.6× 更快、444.6× 更便宜（厂商自述，本库未复跑）。 Vendor claim: ~70–500ms end-to-end; ~$0.042 / MTok input with free output metering; workflow evals claim ~193.6× faster and ~444.6× cheaper vs frontier LLMs (vendor figures, not re-run here).
  • 早期访问：官网 Join Waitlist；适合分类 / 路由 / 打分 / 抽取等可塞进代码的决策，不替代通用聊天或开放式写作。 Early access via the site waitlist; fits classify / route / score / extract decisions inside code — not a general chat or open-ended writing model.

同板相关Related on this board

同一看板上互相关联的卡：社区 demo 指回它跑的模型，模型指向值得看的 demo。Cards linked on this board: a community demo points back to the model it ran on; the model points to demos worth a look.

Strands Agents Strands Agents 官方 Official 社区 showcase Community showcase

Strands Decider 2B：一个小的开源决策模型，只做选择题和打分 Strands Decider 2B: a small open decision model that picks an option or gives a score

Strands Decider 2B: a small open decision model that picks an option or gives a score

Strands Decider 2B 是 Strands Agents 放出的一个小决策模型。它不写文章。你给它一段现状和几个允许的答案，它为每个答案打一个概率，也可以按一个分数尺打分。仓库写它大约 19 亿参数，基于 Qwen3.5-2B 改来，拿掉了原来用来生成文字的那一层，换上一个大约一百万参数的小头。代码和权重以 Apache-2.0 发布，可以在自己的 CPU 或显卡上跑。官博是 2026-10-01，仓库现在指向的参考版本是 v21，更早的 v19 仍在。本库没有安装，也没有复跑仓库里的分数。 Strands Decider 2B is a small decision model from Strands Agents. It does not write prose. You give it a situation and the answers you allow, and it returns a probability for each one, or a score on a scale. The repo says it has about 1.9 billion parameters, starts from Qwen3.5-2B, removes the layer that used to generate text, and adds a small head of about a million parameters. Code and weights are Apache-2.0, and it can run on your own CPU or GPU. The blog is dated 2026-10-01. The repo’s reference version now is v21, and the earlier v19 is still published. This library did not install it and did not re-run the repo’s scores.

厂商公告Vendor announcement 2026年10月1日 Oct 1, 2026 4 官方 · 1 社区 4 official · 1 community
kouhxp kouhxp 官方 Official 社区 showcase Community showcase

Gutsy：本机 CPU 可跑的 0.8B Jev 兼容决策模型 Gutsy: 0.8B Jev-compatible decision model for local CPU

Gutsy: 0.8B Jev-compatible decision model for local CPU

kouhxp 开源的 gutsy-0.8b（v0.4）：把 Qwen3.5-0.8B 微调成决策模型，不生成自由文本。你送一段状态（文本或 JSON）和 typed questions（yes/no、choice、score），它为每个选项返回校准概率；choice / score 还带 reject。运行时 gutsy-inference 走 llama.cpp，默认可在普通 CPU 上起本地 HTTP；接口刻意对齐 Jev / System One（`/v1/systemone` 等），现有客户端多半只换 base URL。权重在 Hugging Face kouhxp/gutsy（Q8_0 与 Q4_K_M GGUF），代码与权重 README 写 Apache-2.0。JevBench / 评测表与延迟是作者自测，本库未复跑。同板与 Jev、Laya、Clef、Jeeves、Ollaya 相邻；Cases 已有本机 Jeff 与 Onesie CLI。 kouhxp’s open gutsy-0.8b (v0.4) fine-tunes Qwen3.5-0.8B into a decision model that does not generate free text. You send a state (text or JSON) plus typed questions (yes/no, choice, score) and get a calibrated probability for every option; choice / score answers also carry reject. The gutsy-inference runtime uses llama.cpp and can serve a local HTTP API on an ordinary CPU. The API deliberately matches Jev / System One (`/v1/systemone` and related), so many existing clients only need a new base URL. Weights live on Hugging Face kouhxp/gutsy (Q8_0 and Q4_K_M GGUF); README says Apache-2.0 for code and weights. JevBench / eval tables and latency are author self-tests, not re-run here. On this board it sits next to Jev, Laya, Clef, Jeeves, and Ollaya; Cases already lists local Jeff and the Onesie CLI.

厂商公告Vendor announcement 2026年10月1日 Oct 1, 2026 2 官方 · 1 社区 2 official · 1 community
ConvAI Innovations ConvAI Innovations 官方 Official 社区 showcase Community showcase

Laya：开源 System 1 决策引擎（对照 Jev） Laya: open-source System 1 decision engine (Jev-adjacent)

Laya: open-source System 1 decision engine (Jev-adjacent)

作者称 Laya 是非自回归、亚 35ms 的开源 System 1 决策模型族（Apache 2.0 权重），提供 choice / score / noul 三类结构化决策与多语路由；对照站内已收录的 TypeSafe Jev。基准、延迟、与 Jev 对比数字一律标「作者称 / 第三方整理」，本库未复跑。HN 讨论：https://news.ycombinator.com/item?id=49765348（2026-09-19）。 Author presents Laya as an open-weight non-autoregressive System 1 decision family (Apache 2.0) with choice/score/noul primitives and multilingual routing; sits next to catalogued TypeSafe Jev. Latency/benchmark/Jev-comparison figures are author or third-party claims — not re-run here.

厂商公告Vendor announcement 2026年9月19日 Sep 19, 2026 1 官方 · 2 社区 1 official · 2 community
ollaya-dev ollaya-dev 官方 Official 社区 showcase Community showcase + 精选 + Featured

Ollaya：本机跑开源决策模型（Jev / Laya 相邻） Ollaya: run open decision models locally (Jev / Laya-adjacent)

Ollaya: run open decision models locally (Jev / Laya-adjacent)

HN 首页 https://ollaya.dev/ — 作者定位「像 Ollama 跑 LLM 一样，本机跑开源决策模型」。拉 Laya / decider / NLI / GLiClass 等开源权重，本地 daemon 提供 TypeSafe 兼容的 /v1/systemone；官方称可改 TYPESAFE_BASE_URL 指向本机，现有 Jev 客户端不用改代码。延迟对比数字（如 Laya 8–10ms、Jev hosted 236–276ms）一律标官网自述 / 第三方基准，本库未复跑。 the site says existing Jev clients work by pointing TYPESAFE_BASE_URL at localhost. Latency comparisons (e.g. Laya 8–10ms, Jev hosted 236–276ms) are site or third-party claims — not re-run here. not a separate card.

厂商公告Vendor announcement 2026年9月25日 Sep 25, 2026 2 官方 · 1 社区 2 official · 1 community
TypeSafe AI TypeSafe AI 官方 Official 社区 showcase Community showcase + 精选 + Featured

Jev 玩宝可梦红（社区 live demo） Jev Plays Pokémon Red (community live demo)

Jev Plays Pokémon Red (community live demo)

Show HN https://jev-pokemon.vercel.app/ — 社区 live：用 TypeSafe Jev 决策模型通关《宝可梦 红》。作者称 harness 只读 Game Boy RAM、列出合法选项与事实，由 Jev 选一项再按键；无脚本通关、不写内存。直播页自称默认静音、右侧显示每次决策与概率；页内有 Frigade 推广条，且写明与任天堂 / Game Freak / The Pokémon Company 无关、不附带 ROM。本卡只记 Jev 能力展示，不是可下载的游戏 ROM。 The author says the harness only reads Game Boy RAM, lists legal options with facts, and lets Jev pick one before pressing buttons; no scripted win path, no memory writes. The live page says it starts muted and shows each decision and odds on the right; it also carries a Frigade promo bar and states it is not affiliated with Nintendo / Game Freak / The Pokémon Company and ships no ROM. Catalogued as a Jev capability showcase only, not a downloadable game ROM.

厂商公告Vendor announcement 2026年9月25日 Sep 25, 2026 1 官方 · 3 社区 1 official · 3 community
PostHog PostHog 官方 Official 社区 showcase Community showcase + 精选 + Featured

Jeeves：带推理的开源 Jev 风格决策模型（PostHog） Jeeves: open Jev-style decision model with reasoning (PostHog)

Jeeves: open Jev-style decision model with reasoning (PostHog)

HN https://github.com/PostHog/jeeves — MIT：PostHog 开源的「会先想再决定」的 Jev 风格分类器。README：基于 Qwen3.5-9B（LoRA + pointer head），SFT + CISPO 训练，带 block-4 diffusion drafter；同一请求支持 noul / choice / score，API 与 Jev 同形（`/v1/systemone`）。作者表（thinking、greedy、2560-token 上限；Kev-9B / Jev 列为 Kev 公布数字）：Test overall 0.889 vs Kev 0.822 / Jev 0.857；JevBench overall（231 public）0.935 vs Jev 0.866；JevBench hard 0.865 vs Jev 0.730。延迟自述：无 thinking 约 0.3 s/请求，有 thinking 中位约 3.3 s（单 H100）；需 CUDA（Hopper 才用 FP8 kernel）。权重 https://huggingface.co/PostHog/jeeves。README 写 Inspired by Kev。公开仓与 HF 晚间 GET 200。本库未复跑基准、未代下权重。 README: Qwen3.5-9B with LoRA + pointer head, trained with SFT + CISPO, plus a block-4 diffusion drafter; same request supports noul / choice / score via a Jev-shaped /v1/systemone API. Author table (thinking, greedy, 2560-token cap; Kev-9B / Jev columns are Kev-published): Test overall 0.889 vs Kev 0.822 / Jev 0.857; JevBench overall (231 public) 0.935 vs Jev 0.866; JevBench hard 0.865 vs Jev 0.730. Latency claim: about 0.3 s/request without thinking, ~3.3 s median with it on one H100; needs CUDA (Hopper for the FP8 kernel). Weights at https://huggingface.co/PostHog/jeeves. README says Inspired by Kev. Public repo and HF evening GET 200. Benchmarks not re-run here; weights not downloaded for you.

厂商公告Vendor announcement 2026年9月29日 Sep 29, 2026 2 官方 · 1 社区 2 official · 1 community
Cloudflare Cloudflare 官方 Official 社区 showcase Community showcase

Clef：Cloudflare 开源决策模型（含 Clef-Flash） Clef: Cloudflare open-weight decision models (incl. Clef-Flash)

Clef: Cloudflare open-weight decision models (incl. Clef-Flash)

Cloudflare 发布开源决策模型 Clef，以及更小的 Clef-Flash。它们不生成自由文本：读入一段状态和一组带类型的问题，为每个允许的答案返回概率。Workers AI 上的模型 id 是 @cf/cloudflare/clef（27B）和 @cf/cloudflare/clef-flash（9B）。官方称接口与 Jev / System One 同形，问题类型仍是 noul / choice / score，并带视觉编码器，状态可以是文本、JSON、图像或视频。权重在 Hugging Face，许可 Apache-2.0。HF 卡写 Clef 由 Qwen/Qwen3.8-27B 后训练、Clef-Flash 由 Qwen/Qwen3.5-9B 后训练，这是厂商 / HF 口径。官博还宣布 RL 微调：先由 forward-deployed engineer 动手，之后再做成自助平台——按路线图记，不是已经核过的产品深度。Decision Index、延迟和工作流分数一律是厂商自述，本库未复跑。同板与 Jev、Laya、Jeeves、Ollaya 相邻；Cases 里已有本机 Jeff 和命令行 Onesie。 Cloudflare released the open-weight decision model Clef and the smaller Clef-Flash. They do not generate free text: they read a state plus typed questions and return a probability for every allowed answer. On Workers AI the ids are @cf/cloudflare/clef (27B) and @cf/cloudflare/clef-flash (9B). The vendor says the API matches Jev / System One, with noul / choice / score questions and a vision encoder, so state can be text, JSON, images, or video. Weights are on Hugging Face under Apache-2.0. The HF cards say Clef is post-trained from Qwen/Qwen3.8-27B and Clef-Flash from Qwen/Qwen3.5-9B — a vendor / HF claim. The blog also announces RL fine-tuning: hands-on with a forward-deployed engineer first, then a later self-serve platform. That is a roadmap, not a product depth this library verified. Decision Index, latency, and workflow scores are vendor claims and were not re-run here. On this board it sits next to Jev, Laya, Jeeves, and Ollaya; Cases already lists local Jeff and the Onesie CLI.

厂商公告Vendor announcement 2026年10月1日 Oct 1, 2026 4 官方 · 1 社区 4 official · 1 community