新闻与全站搜索
关联新闻、工具、模型、指南、专题、工作流与提示词。
新闻报道 335
“parallel-code”
b12177
A fix has been implemented to prevent crashes in the command-line interface when encountering invalid UTF-8 in prompts or files, with assistance from Claude. This update is part of the b12177 release of llama.cpp, which includes various binary distributions for macOS, Linux, Windows, Android, and other platforms.
b12179
The update introduces support for 3D convolution (conv_3d) on Hexagon hardware by generalizing the existing conv_2d implementation. It leverages the HMX tiled path, folds kernel dimensions into a virtual row, and uses a shared solver with an is3d flag. The host computes unfold divisors to avoid device-side division, prevents DMA queue overflow, and improves tile size selection based on VTCM usage. Additional changes include handling arbitrary positive strides, preserving load/shuffle paths for small strides, and fixing compiler warnings.
Extend Claude Code to remote sessions on Amazon Bedrock AgentCore with security controls
Run Claude Code as a remote agent on Amazon Bedrock AgentCore. Each coding task runs in its own isolated session in your AWS account, every model call goes through Amazon Bedrock, and the result comes back as a GitHub pull request you review and merge.
How Greenlight Financial built an autonomous SOC solution on Amazon Bedrock AgentCore
Greenlight Financial resolves more than 90% of up to 4,000 monthly security and risk cases without human intervention using Luna, a tiered multi-agent system on Amazon Bedrock AgentCore. This post covers the architecture, episodic memory for continuous learning, and the expansion from SOC operations into financial risk triage.
给AI出的测试题，为什么AI自己批自己能拿满分
你有没有想过一个很怪的问题：如果让一个学生自己出卷子、自己做题、自己打分，这场考试还有意义吗？这正是现在AI圈子里悄悄发生的事情。大模型写代码越来越厉害，很多公司开始让AI自己给自己写的代码配套测试，用来验证代码对不对。听起来挺美好，一个闭环系统，AI写代码，AI写测试，AI自己验证自己。但问题是，验证这个测...
Anthropic 实验：Claude 半年将本金翻六倍
本金 30 亿 ISK半年后 180 亿 ISKAnthropic 让 Claude 在一款游戏里炒了半年的货，最新的 Fable 5 平均把本金翻成了6 倍。 而只比它早发布四个月的 O....
Agents Are Going Async
Async subagents let an agent stay responsive while background workers run long tasks. How the orchestrator, notifications and approvals work in Deep Agents.
Anthropic 推出 Claude 个人理财功能，支持智能消费分析与账单追踪11月5日，Anthropic宣布为Claude推出“个人理财”功能，本周率先在美国面向Pro、Max、Ultra订阅用户灰度测试。该功能支持用自然语言理清个人财务状况，主打绝对安全与客观公正，标志大模型正从办公创作助手延伸至日常金融与生活管理场景。 刚刚 3.4K
人工智能企业Anthropic于11月5日宣布为Claude推出全新个人理财功能，面向美国地区的Pro、Max及Ultra订阅用户开放灰度测试。该功能允许用户通过自然语言对话安全绑定银行卡，实现支出分类统计、异常账单识别、财务术语解释与定制化数据看板生成，强调仅具只读权限，不提供投资建议，确保资金安全与分析客观性。官方提醒用户核对关键数据，避免依赖模型输出。
b12141
The latest update to llama.cpp introduces reference-counted checkpoints instead of deep-copies, reducing memory overhead and improving efficiency. This change adapts the slot save/restore checkpoint mechanism to shared_ptr checkpoint lists and common_state_data buffers, with contributions from multiple developers and AI assistants.
b12142
A fix was implemented to verify the combined K+V f16 scratch size in the Flash Attention dequantization path for Vulkan, addressing issue #30048.