Prepping slides & demos for my Voxxed Days Amsterdam 2026 deep dive tomorrow
Packing in Memory, Advisors, RAG, Tool Calling & MCP, Agentic Patterns, A2A & ACP, LLM-as-a-Judge, Guardrails… and somehow fitting it all into 2 hours!
See you there 👉 https://t.co/6tzbxGNClP
File-based long-term memory for @SpringAI agents - no vector store, no database, just files.
Plain Markdown files, MEMORY.md index, the agent manages it all via tool calls. Claude auto-memory compatible but portable to any LLM provider.
📖 https://t.co/j3ZQKL7uQE
#Java#AI
A PaaS that runs data streaming pipelines? Sure. The 4th part of my blog series looks at @springcloud Data Flow on @cloudfoundry, and performing real-time processing ... https://t.co/sPSVylOYmA
You could call tools. You couldn't build on top of tool calling! #SpringAI 2.0 lifts the tool loop out of the chat models and into the advisor chain - composable, observable, replaceable: https://t.co/gCiRQFVuST
@SpringAICentral#MCP
前些天 X 上还一堆人讨论要不要看 AI 生成的代码,现在《Clean Code》作者鲍勃大叔都说:“我不看 AI 写的代码”
他的原话是,这是他能利用 AI 生产力的唯一方式。人类读代码太慢了,如果还逐行审查,就丧失了用 AI 的意义。
但不看不等于不管。他的做法是给 AI Agent 设置层层关卡:单元测试、Gherkin 测试(一种用接近自然语言描述软件行为的测试格式)、QA 流程、代码质量指标、变异测试(故意往代码里塞小错误,看测试能不能抓住)、测试覆盖率,等等。
他在今年早些时候还公开了自己的具体实践:一套四个 Agent 组成的流水线,分别负责需求规格化、编码、重构和架构审查,每个阶段都比上一个阶段更形式化,需要的人工干预也更少。他同时还会看测试覆盖率、依赖结构、圈复杂度、模块大小这些指标,从指标推断代码质量,而不是从代码本身。
【注:圈复杂度(Cyclomatic Complexity)衡量代码中独立执行路径的数量,数字越大说明逻辑越复杂,越难维护和测试。】
当 AI 生成代码的速度远超人类阅读代码的速度,代码审查的形态也在跟着改变。以前的核心能力是读代码、写代码,现在可能正在变成写测试、定约束、设指标。鲍勃大叔过去几十年一直在推测试驱动开发(TDD),现在 AI 时代高质量的测试覆盖反而比代码更有价值。
他今年在 O'Reilly 上开了一门课,叫《AI Agents for Clean Code》,也在自己的 Clean Coders 平台推出了新系列《Clean AI: Agentic Discipline》。主旨一样:AI Agent 不是不需要纪律,是需要不同的纪律。
Introducing Kimi K3: Open Frontier Intelligence
🔹 2.8 Trillion Parameters, 1 Million Context, Native Multimodal
🔹 Kimi Delta Attention enables up to 6.3x faster decoding in million-token contexts
🔹 Attention Residuals deliver ~25% higher training efficiency at <2% additional cost
🔹 Built for long-horizon agentic coding and self-evolving workflows
Kimi K3 is now live on on https://t.co/zrk6zZxZUo, Kimi Work, Kimi Code, and the Kimi API.
Open Weights by July 27, 2026.
🔗 API: https://t.co/XCrgjXAqMw
🔗 Tech blog: https://t.co/YTfiMSNM1f