广场

Trusting Trustworthiness: Zero Trust, Trust by Default, and the People Who Wrote the Software

“Perhaps it is more important to trust the people who wrote the software.” Ken Thompson, Reflections on Trusting Trust (1984) Suppose an actor’s values are genuinely positive. They do not seek domination, personal enrichment, or the suffering of others. They sincerely want to protect what is valuable, reduce harm, and leave the world better than they found it. Would that underlying tendency make them trustworthy even when a particular decision

The best dark mode toggle is probably none

About a month ago, I wrote an article recommending that if you are going to have an always visible control for switching between light and dark mode, it should be a two-state toggle that alternates between system and whatever the current opposite of system is , not a tri-state one (system, light, dark). If you are forced to include such a control (say, someone is pointing a gun at you and shouting “code dammit! now!” ), I stand by that recommendation: use two states, as described in the article. But the article explicitly doesn’t answer the question “should you have one at all?” . I was much more neutral on this at the time of writing. I am now firmly in the “no” camp. More on that below. Th…

Lea Verou开发技术英文

关于传统产品方法在AI时代延续发展的思考

当Agent需要逐一调用多个API才能回答用户问题时,效率与成本成为瓶颈。本文通过一个真实案例,揭示如何通过封装中间层将决策次数从多次降为一次,从而让Agent“少想几步”。作者还从传统分层架构的视角,剖析了AI时代模型作为新前端对聚合层的必然需求,并给出了三条实用的封装原则。 ——让 Agent 少想几步,效率自然就上去了 工作中的一个实例场景 最近在做接入第三方API接口的需求,目前我们的平台已经能够支持用户按自己的需要将多个API接口直接打包成一个MCP接口,直接通过AI助手调用。 最初的想法是直接将所提供的API接口都接回来,由用户根据需要打包MCP接口,这样的方式可以更加灵活。但是在沟通的过程中发现,用户更希望直接用一些现成的东西去执行他所需的业务流程。直接交付原子API的时候,用户得自行判断哪些接口该放一起、工具叫什么名字、描述怎么写等等一系列问题。另一方面,用户组装的API接口本质上并没有减少agent的思考。 举个简单的例子:假设用户自己组装的MCP接口包含“实时行情、历史日K、历史分钟K”3个API,在接收到query时(比如:机器人概念和固态电池概念今天表现怎么样?各自涨了多少?),Agent思考过程中需要先判断走哪个服务,再需要逐一调用这3个API接口的详情并判断是否能够回答用户的问题,怎么回答。 我们把设计决策推给了用户,用户又把它推给了模型。 于是我们调整了实现方案,考虑在技术层面直接先封装一层API接口,再将中间层给出去。这样做有什么好处?还是上面这个例子,我们把“实时行情、历史日K、历史分钟K ”合成一个“行情”API接口。在接收到query时(比…

人人都是产品经理产品设计中文

Think Once, Act Fast: Cost-Effective Recursive Self-Improvement for Decision Model Harness

arXiv:2611.22432v3 Announce Type: replace Abstract: Fast System-1 models enable responsive actions but struggle with complex or unfamiliar tasks. Large language model (LLM)-based System-2 provides strong reasoning capabilities, yet repeated invocation incurs substantial latency and computational costs. To bridge this gap, we propose JevRSI, a System-1/System-2 collaboration framework that transforms LLM reasoning into transferable decision support through recursive harness improvement. A Jev-style System-1 model enables low-latency action selection, while an asynchronous System-2 LLM develops a modular harness. The harness integrates procedures, state memory, and world models to provide deci…

arXiv AIAI 研究英文

Metals losing their shine? Tata Steel, Vedanta, other stocks fall up to 7% in 5 days as metals hit multi-month lows. What analysts say

Recent trends indicate a notable decline in metal prices, leading to a subsequent downturn in stock valuations within the sector. Traders are anticipating a potential interest rate hike from the Federal Reserve in the forthcoming session. While Indian producers are witnessing a squeeze in earnings and margins, the domestic demand remains consistent.

Economic Times财经资讯英文