LeituraPesquisaRadarFramework de investimento
Entrar / Cadastrar
← Voltar para a leitura
NotíciasTópico · Clairic提取模型Material1 min de leituraEditorial DisconfirmAI

Cloudflare debuts Clairic: A System One extraction model that skips token generation

Cloudflare has launched a preview of Clairic, a new 'System One' extraction model designed to pull typed values with confidence scores from unstructured data in a single forward pass, claiming faster and cheaper performance than traditional LLMs.

2026-10-20 01:48 GMT+8

US cloud computing company Cloudflare announced the preview of Clairic on October 19, 2026, defining it as a new class of 'System One extraction models.' The model is designed to extract, compute, estimate, and forecast values directly from unstructured inputs like receipt photos, support emails, or CSV files, rather than generating text word-by-word like Large Language Models (LLMs).

According to Cloudflare's official blog, Clairic operates via a single parallel forward pass without producing output tokens, meaning it charges only for input and typically responds in under a second. It returns typed values (such as numbers, dates, and lists) with character offsets and confidence scores, returning null if an answer cannot be found. This design avoids common LLM failure modes like invalid JSON formatting and hallucinations, although the model can still make mistakes.

The concept follows TypeSafe's release of Jev a month prior, which introduced decision models based on Daniel Kahneman's 'System 1' thinking from Thinking, Fast and Slow. Cloudflare states that Clairic is the first model in this new extraction category, specifically targeting tasks that require concrete numerical answers rather than choices or free-form text. Clairic is currently hosted on Workers AI, with plans to release open weights soon.

Fontes

Entrar / Cadastrar
LeituraPesquisaRadarFramework de investimento
blog.cloudflare.com
↗
Tópico

Clairic提取模型

Cloudflare于2026年10月19日推出Clairic预览版,这是首个“System One”类提取模型。与逐字生成文本的大语言模型(LLM)不同,Clairic通过单次前向传播直接从非结构化输入中提取、计算和预测类型化数值(如发票…

4 etapas1 peçasAtualizado 2026-10-24 01:06

Como chegamos aqui

  1. 2026-09-15TypeSafe公司引入“System One”模型概念并发布Jev决策模型,为后续提取模型铺路。blog.cloudflare.com ↗
  2. 2026-10-01Cloudflare发布Clef和Clef-flash决策模型,并在Hugging Face开源,确立了System One生态中的决策环节。unite.ai ↗
  3. 2026-10-19Cloudflare正式宣布Clairic预览版上线Workers AI,定位为System One提取模型,支持文本、图像输入及多种类型化输出。developers.cloudflare.com ↗

O que ainda está indefinido

  • Clairic开放权重(Open Weights)的具体发布日期尚未确定,仅表示“soon”。
  • 第三方独立基准测试是否证实了Cloudflare声称的49%成本降低和3.2倍速度提升?
  • 在处理多步依赖计算时,Clairic与外部代码执行的集成最佳实践是什么?
Ler o tópico completo →
Continuar pesquisando →