@__oQuery: Everyone says K3 is easy to use, so I opened one and tried the latest Kimi Code. But I found that Kimi's development team might really not have a good feel for design. As soon as I started using it, I noticed many frustrating issues: 1. The ask user question in figure one…
Summary
User posts criticism of Kimi Code's interaction design, pointing out issues such as the unreasonable submission method of the ask user question tool and the state bar shaking due to container height changes during command selection, hoping the Kimi team will optimize.
View Cached Full Text
Cached at: 07/17/26, 12:19 AM
People are saying that K3 is great to use, so I tried the latest Kimi Code. But I found that the Kimi development team might not really have a good sense for design. Right from the start, I noticed several frustrating issues:
-
The “ask user question tool” in Figure 1: I had no idea how to submit at first, because pressing Enter triggers a reverse selection. I only realized after a few looks that submitting requires pressing Tab – an interaction that is placed in the same column as the Tab key. This is clearly unreasonable.
-
The selection in Figure 2 after entering command mode: when scrolling up and down, the height of the scroll container changes, causing the status bar at the bottom to jump up and down constantly. I don’t understand what purpose it serves. This is clearly CLS.
I hope the Kimi team can optimize this.
Similar Articles
@hhmy27: Quick take on coding with Kimi k2.6 — this drop is all about better taste. I just vibed out the Interface Craft page animations and the result feels legit. Peeked at the code: it’s leaning on Framer and GSAP, so the motion actually feels polished.
Kimi k2.6 levels up aesthetic coding, spinning out slick Interface Craft page animations powered by Framer and GSAP.
@skirano: Introducing Kimi 2.6 Code. A Claude Code-like terminal experience built specifically for Kimi K2.6, effectively making …
Kimi 2.6 Code is a Claude Code-like terminal experience built specifically for the Kimi K2.6 model, positioning it as one of the most powerful open-source coding agents available.
@berryxia: OMG, I'm totally blown away by Kimi 3! Incredible. It feels like it crushes Kimi 2.7! Let's first look at the test with the same prompt on the previous 2.7 model.
After testing Kimi 3, the user found its performance far exceeds the previous generation Kimi 2.7, calling it a 'crushing' victory, and mentioned that a demo is already available on the official website.
Kimi K2.7 Code feels more useful than flashy
Kimi released K2.7 Code, a coding-focused AI model with improved benchmarks and 30% lower thinking token usage, emphasizing practical performance in long coding loops and agent tool integration rather than flashy scores.
@berryxia: Looks like Kimi has been quietly making big moves. After watching these demo videos, my back didn't get cold — instead, I got pumped and felt truly impressed! Kimi today directly upgraded AI agents from "just chatting" to "operating browsers like humans." They released the Web Bridge browser extension.
Kimi has released the Web Bridge browser extension, enabling AI agents to operate browsers like humans, performing tasks such as searching, scrolling, and clicking, while supporting multiple AI tools.