Blog

14 articles

Nov 08, 2026中文 · EN

AIAgents

Session Engineering（二）：加一层总办，人只对接一个会话

11 月 7 日晚上，要我处理的事攒了二十多件，分散在十几个会话里。之后我们加了一层总办：各会话把要我定的事发给总办，总办整理到一个待办页，我在手机上点选、统一发送，再由总办转回各会话执行。本文写这一层怎么运转：请求怎么写，总办怎么分流，转达的决定怎样算数，会话之间的消息额度，以及几项可以对照的历史制度。

AIAgents

Session Engineering, part 2: one session between me and the rest

On the night of Nov 7, more than twenty items waiting for me had piled up across a dozen-plus sessions. We then added a chief-of-staff layer. Sessions send what needs my decision to the chief of staff, which collects it on one page; I go through the options on my phone and send them in one batch, and the chief of staff relays each decision back for execution. This post covers how the layer works: how requests are written, how the chief of staff filters them, when a relayed decision counts, message quotas between sessions, and a few historical institutions to compare it with.

Nov 06, 2026中文 · EN

AIAgents

Session Engineering：组织多个 Agent 会话，也是管理自己的上下文

一个 Agent 已经能独立做完一件完整的事，限制变成了人能同时跟住几个会话。我把围绕这个限制组织多个 Agent 会话的做法叫作 Session Engineering：它决定工作怎样分给会话，也决定人每次切换时要重新读多少东西。本文说明它和 Prompt、Context、Harness、Loop Engineering 的区别，以及 Tenon AI 按这套做法运转时定下的规则。

AIAgents

Session Engineering: organizing agent sessions is also managing your own context

An agent can now finish a complete piece of work on its own, so the limit has become how many sessions one person can keep track of. I call the practice of organizing agent sessions around that limit Session Engineering. It decides how work is split across sessions and how much a person has to reread at each switch. This post compares it with Prompt, Context, Harness and Loop Engineering, and describes the rules Tenon AI runs on.

Oct 31, 2026中文 · EN

把每一次交互写进模型

我想要的个人 AI 只有一个要求：每一次交互都影响下一次交互，记忆不放在有限的上下文里，而是进入模型本身。本文解释模型为什么记得住世界知识却记不住你，上下文、记忆表和权重的本质关系，已有工作做到了哪里，以及一种两层参数记忆的方案。

Writing every interaction into the model

The personal AI I want has one requirement. Every interaction affects the next one, and memory lives in the model itself and not in a limited context. This post explains why models remember world knowledge but not you, how context, memory tables and weights relate, what existing work has achieved, and a two-layer design for parametric memory.

Oct 31, 2026中文 · EN

动态智能：让模型在运行中改变自己

今天的大模型把智能分成两段：训练时写入，推理时只读。动态智能（Dynamic AI，DAI）取消这个分隔，运行本身就会改变模型。本文说明它和 Harness、微调、持续学习、RSI 的区别，它要写入什么，为什么还没有出现，可能的架构，以及它能否带来持续进化。

Dynamic intelligence: models that change as they run

Today's large models split intelligence into two phases, writing during training and read-only during inference. Dynamic intelligence (Dynamic AI, DAI) removes that split, so running changes the model. This post explains how it differs from harnesses, fine-tuning, continual learning and RSI, what it needs to write, why it does not exist yet, a possible architecture, and whether it could lead to sustained evolution.

Oct 23, 2026中文 · EN

AIJev

老框架，新部件：用 Jev 让概率模型自己建、自己更新

用大量是否命题建一个领域模型，用 Jev 估计概率，把现实中发生的事件作为证据输入，实时更新对未来的预测。这类模型已有四十多年的成熟框架，没有普及是因为建模和维护太贵。Jev 能把其中两个最贵的环节自动化：估计概率，以及把文字消息转成证据。

AIJev

Old frameworks, a new part: letting probability models build and update themselves with Jev

Build a domain model from many yes/no propositions, have Jev estimate the probabilities, feed real-world events in as evidence, and update forecasts in real time. Mature frameworks for this have existed for more than forty years; they never spread because building and maintaining models was too expensive. Jev can automate the two most expensive steps, estimating probabilities and turning written messages into evidence.

Oct 23, 2026中文 · EN

AIJev

Jev 能用来做什么：从概率门到可计算的信念模型

总结前两篇的理论和实验，提出一种分工：Jev 只估计最基础的概率，组合与推断全部交给数学，准确度靠真实数据校准。按这种分工，可以把大模型的知识整理成一个彼此自洽、可以编辑和推演的概率模型。文章讨论它和直接问大模型的区别，以及几类应用方向。

AIJev

What Jev can be used for: from probability gates to computable belief models

This post brings together the theory and experiments of the previous two and proposes a division of labour. Jev estimates only the most basic probabilities, math does all combination and inference, and real data calibrates accuracy. With this split, a language model's knowledge can be turned into a probability model that is self-consistent, editable and explorable. It discusses how this differs from asking a language model directly, and several application areas.

Oct 23, 2026中文 · EN

AIJev

概率门实验：Jev 的概率能直接用吗

用真实的 Jev 做了三组实验：它给出的概率是否自洽，能不能当条件概率的来源，分步组合是否比直接问更准。结论是排序很准、数值偏向中间，少量真实数据就能校准；组合本身不提高精度，同向偏差会原样传下去。

AIJev

Probability gate experiments: can Jev's probabilities be used as they are?

Three experiments with the real Jev test whether its probabilities are self-consistent, whether it can serve as a source of conditional probabilities, and whether composing an answer in steps beats asking directly. It ranks well but pulls values toward the middle, and a small amount of real data is enough to calibrate it; composition by itself does not improve accuracy, and bias in a shared direction passes straight through.

Oct 23, 2026中文 · EN

AIJev

概率门：从比特到概率的电路

逻辑门把电压翻译成 0 和 1，Jev 把用语言描述的世界翻译成概率。本文把 Jev 看作一种「概率门」，参考随机计算、贝叶斯网络和概率比特的已有工作，讨论可以用它组合出哪些元件，以及怎样用这些元件搭一个世界模拟器。

AIJev

Probability gates: from bits to probabilities

Logic gates turn voltages into 0 and 1; Jev turns a description written in language into probabilities. This post treats Jev as a "probability gate", draws on prior work in stochastic computing, Bayesian networks and probabilistic bits, and looks at which components can be built from it and how they could form a world simulator.

Oct 13, 2026EN

AIAgents

AgentHub: operating and coordinating a fleet of Codex agents

A product-change walkthrough shows how AgentHub combines fleet management, authorised agent-to-agent delegation and sequential workflows around the same deployed agents.

Oct 12, 2026EN

AIAgents