---
format: "aidr-story-markdown/v1"
id: "c1ffc7ee01d52dc2093f524287362b3d23121804ce2887251aff080a265b449b"
canonical_url: "https://aidr.today/c1ffc7ee?lang=en"
title: "Tencent's Gander aims to keep talking while it works in the background"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-20T15:33:30.000Z"
category: "Models"
topics: ["tencent","gander","multi-agent","inference","benchmark"]
source_urls: ["https://the-decoder.com/tencents-gander-aims-to-keep-talking-while-it-works-in-the-background/"]
summary: "Tencent's Gander combines real-time conversation with AI agent capabilities. A \"cerebellum\" handles the conversation while a swappable \"brain\" tackles complex tasks in the background. Users can interrupt at any time. In benchmark tests, Gander interrupted users in just 8 percent of cases, though it still trailed competitors on task accuracy. The article Tencent's Gander aims to keep talking while it works in the background appeared first on The Decoder ."
---

# Tencent's Gander aims to keep talking while it works in the background

> [Open the canonical story](<https://aidr.today/c1ffc7ee?lang=en>)

**Published:** 2026-09-20T15:33:30.000Z
**Category:** Models
**Topics:** tencent, gander, multi\-agent, inference, benchmark

## Summary

Tencent's Gander combines real\-time conversation with AI agent capabilities\. A "cerebellum" handles the conversation while a swappable "brain" tackles complex tasks in the background\. Users can interrupt at any time\. In benchmark tests, Gander interrupted users in just 8 percent of cases, though it still trailed competitors on task accuracy\. The article Tencent's Gander aims to keep talking while it works in the background appeared first on The Decoder \.

## Sources

- [Story source](<https://the-decoder.com/tencents-gander-aims-to-keep-talking-while-it-works-in-the-background/>)