返回资讯中心
外部精选
软件工程
#开发者实时流

Minmax matrix: Desk routing went from 11% to 90%"

VEKTOR 2.0.1: Desk routing went from 11% to 90%. Measured via Minimax matrix

Hacker News 最新vektormemory2026/10/18 · 2026/10/1816 分钟阅读

以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。

LLM

Jev

Clef

Agentic Ai

VEKTOR 2.0.1: Desk routing went from 11% to 90%. Measured via Minimax matrix

Vektor Memory

13 min read·

Just now

--

Before this release, Desk’s automatic routing ran the right mode for about 11 of every 100 messages that needed one. In our test it was 15 of 133.

Desk has eight modes: ordinary chat, Council, Critique, Collab, Agent, Coach, Crucible and Cadence. Council compares options. Critique challenges a plan. Coach helps you sort out your priorities. Each one gives better answers to the right kind of question, but each sat behind a choice you had to remember to make.

A message like "Should we choose Jev or Clef, give me different viewpoints” gets a better answer from Council, and only someone who knows Council exists will open it.

So for 2.0.1 we changed who makes the choice. Desk now reads your message, picks the mode, and tells you what it did. This post covers three things: what we built, why we trust it enough to let it run without asking, and what we measured, including where it still gets things wrong.

Updated Desk v2.0.1

What we measured

We tested this on 330 messages we wrote ourselves. About 9 in 10 of the messages that needed a mode went to the right one, up from about 1 in 10 before. Fewer than 2 in 100 automatic runs were wrong. The decision takes about a third of a second and happens on your own computer, so the text of your message stays there.

Our test messages are ours, so real use will probably land a few points lower. The undo chip counts every time someone reverses a routing, and that count will show us the real rate.

  1. Speed, and the fast tier for small jobs

Press enter or click to view image in full size

  1. Vektor decide: sort your own text into your own labels

Press enter or click to view image in full size

  1. Final choice on CLINC150: the minimax matrix

Press enter or click to view image in full size

A. Full results: Desk routing and decision speed

Press enter or click to view image in full size

B. Full results: the fast tier and release checks

Press enter or click to view image in full size

C. Full results: CLINC150

Press enter or click to view image in full size

D. Full results: When2Call and BANKING77

Press enter or click to view image in full size

E. Full results: the router head and other tries that did not ship

Press enter or click to view image in full size

F. Full results: Vektor decided and hosted pickers

Press enter or click to view image in full size

G. Final choice on CLINC150: the minimax matrix (with the hosted model named)

Press enter or click to view image in full size

How it works

Four signals, one decision. Desk looks at the words you used, a set of rules for strong phrases, a small embedding model that shortlists the three most likely heavy modes, and the local language model, which picks one from that shortlist or says “ordinary chat”.

The model answers one narrow question. Choosing among four options is far easier than open-ended chat, which is why it takes about 0.3 seconds on a local GPU.

A policy decides run or suggest. If you name a mode, it runs. Coach, Critique, Crucible and Cadence run on the model’s word, because a wrong guess costs one extra reply. Council and Collab run only when the model is at least 90% sure of its own pick. In our tests its stated confidence matched how often it was right, within 3.2 points.

Agent never runs on one signal. It can change things, so it always needs a second one, and you get a one-click chip instead.

Everything else becomes a chip. If the signals disagree, you see a suggestion and nothing runs.

Every automatic run can be undone, and the app counts how often it is. Turn the whole feature off with “Let Desk run the mode for me” in Preferences.

The fast tier is separate and opt-in. If you pick a cheaper model for small jobs, a local yes/no question decides which jobs qualify. Anything about your own history (“what did I say about…”) always stays on the main model, because that is where your memory is.

Release checks. More than 200 test suites pass before a build ships. We replay 330 saved answers through the routing rules, and a live check with the real model fails the release if wrong automatic runs pass 3% or coverage drops by 2 points.

Privacy. By default nothing leaves your computer. An optional hosted decision model exists, but it needs a consent box, sends only the text of the one message (up to 1,200 characters), and falls back to the local model if it fails or runs out of free allowance.

How we chose this approach

Every design question in this release was settled with the same small method, a minimax matrix skill file included.

Why this was the right way to work: it stopped us shipping three ideas that looked sensible and measured worse, and it made us say out loud where we overrode the numbers. Live runs also found two bugs that 37 unit tests missed, a cold model that never finished loading and a deleted line that returned the model’s answer.

Customers can also use the idea directly. 2.0.1 adds vektor decide: write a small JSON file with your text and your own labels, and your local model answers with a choice, a yes or no, or a score, each with a probability.

It is the same request shape the hosted decision services use, so a file written for it carries over. On a public set of 151 categories it was right about 9 times in 10, in about a third of a second, and the --eval option measures it on your own labelled sample. Nothing leaves your computer.

You can use the same method yourself. The minimax-matrix skill ships with 2.0.1.

Ask Desk a question like “keyword search or embeddings, we care about accuracy and speed” and it builds the matrix, tests in stages, scores small samples cautiously, and tells you whether to switch or keep what you have.

The skill’s reference page walks through the small-jobs decision above, step by step, with the real numbers.

We will keep adding functions as we get feedback. Chrome automation, enterprise controls, more games and a game-pack format, and faster local inference are on the list for the next release.

Version 2.0.1 is on the downloads page: https:www.vekmem.com

Run your own race, and keep your own data.

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →