AI 每日快讯

AI 每日快讯

AI 产品、模型、开源工具和官方动态的时间流。保留历史记录,按分类、日期和标签继续筛选。

3781历史快讯
208开源工具
8当前结果
09 月 29 日 2026-09-29 快讯
MarkTechPost 官方资讯

MarkTechPost:Liquid AI Releases d1: A Decision Model That Returns Calibrated Probabilities With Zero Outp…

原文摘要:Liquid AI has released d1, a decision model built for structured choices instead of text generation. You give it context and a set of typed questions. It returns calibrated probabi 来源:MarkTechPost。建议继续查看原文,重点核对它影响的工具入口、成本、风险和真实使用场景。

MarkTechPost 官方资讯

MarkTechPost:OpenAI Launches dots: Always-On GPT-6 Astra Agents That Work From Their Own Cloud Computers

原文摘要:OpenAI just introduced dots at their DevDay today. Dots are persistent AI agents powered by GPT-6 Astra. Each dot gets its own cloud computer and browser. It works across 4,000+ ap 来源:MarkTechPost。建议继续查看原文,重点核对它影响的工具入口、成本、风险和真实使用场景。

MarkTechPost 官方资讯

MarkTechPost:Nebius Opens 2026 Physical AI Awards: Five $150K Compute Prizes, Nine Judges, and an October…

原文摘要:Nebius and NVIDIA are running the 2026 Physical AI Awards for startups with products in the field. Five category winners each get $150,000 in compute credits, joint promotion, exec 来源:MarkTechPost。建议继续查看原文,重点核对它影响的工具入口、成本、风险和真实使用场景。

MarkTechPost 官方资讯

MarkTechPost:Google Research Open-Sources RRSI: AI Agents That Improve Their Own Harness Without Overfitt…

原文摘要:Google Cloud AI Research has open-sourced RRSI, a framework that lets LLM agents rewrite their own prompts, tools and memory while model weights stay frozen. It adds a leakage crit 来源:MarkTechPost。建议继续查看原文,重点核对它影响的工具入口、成本、风险和真实使用场景。

MarkTechPost 官方资讯

MarkTechPost:H Company Releases Holo4: Open-Weight Computer-Use Models That Click, Code and Call Tools Ac…

原文摘要:H Company has released Holo4, a family of generalist computer-use models for AI agents. One set of weights clicks and types on screens. It also writes code and calls MCP or API too 来源:MarkTechPost。建议继续查看原文,重点核对它影响的工具入口、成本、风险和真实使用场景。

阿里 Qwen 发布 Qwen-Audio-3.1-Realtime:全双工语音模型会思考、会调工具、会判断何时开口

阿里 Qwen 团队发布了 Qwen-Audio-3.1-Realtime,这是一个全双工语音模型,被训练成能推理、调用工具并自行决定何时说话。原始信息给出的数据是:在 τ-Voice 适配任务上成功率从 78.4% 提升到 82.0%,对背景人声的误回应从 73% 降到 13%,目前已作为 API 在 QwenCloud 上线。值得关注的是,「何时开口」这个判断能力直接关系到语音助手的自然度,误回应大幅下降意味着在嘈杂环境里更可用,而工具调用则让它不止于聊天。受影响的主要是做实时语音交互、智能客服和语音 agent 的开发者。下一步建议在 QwenCloud 上申请 API,用真实噪声环境和多轮打断场景测试其响应时机与工具调用稳定性。

MarkTechPost 官方资讯

MarkTechPost:Anthropic Releases Claude Sonnet 5.5: 70.6% on Terminal-Bench 4.0 at the Same $2/$10 Price

原文摘要:Anthropic has released Claude Sonnet 5.5, the second model in its Claude 5.5 family. It scores 70.6% on Terminal-Bench 4.0 and lands within 2 points of Opus 5.5 on GDPval-AA. It al 来源:MarkTechPost。建议继续查看原文,重点核对它影响的工具入口、成本、风险和真实使用场景。