<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Models on Lynx Tech Blog</title><link>https://blog.lynxflow.co/en/tags/models/</link><description>Recent content in Models on Lynx Tech Blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><lastBuildDate>Mon, 10 Aug 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://blog.lynxflow.co/en/tags/models/index.xml" rel="self" type="application/rss+xml"/><item><title>It Won't Do It Unless I Ask: My First Few Days with deepseek-v4-flash</title><link>https://blog.lynxflow.co/en/posts/deepseek-v4-flash-no-ask-no-do/</link><pubDate>Mon, 10 Aug 2026 00:00:00 +0800</pubDate><guid>https://blog.lynxflow.co/en/posts/deepseek-v4-flash-no-ask-no-do/</guid><description>&lt;img src="https://blog.lynxflow.co/images/deepseek-v4-flash-no-ask-no-do.png" alt="Featured image of post It Won't Do It Unless I Ask: My First Few Days with deepseek-v4-flash" /&gt;If I Don’t Ask, It Doesn’t Act I recently switched to a new model for work: deepseek-v4-flash-0731.
After using it for a few days, I’ve figured out its temperament: if I don’t ask, it doesn’t act.
Tell it to fix a bug, and it fixes only that bug. Three lines away there might be an obviously explosive bit of code, but if I don’t call it out, it won’t touch it. Once it’s done, it won’t ask a follow-up either—things like “Want me to add a test while I’m here?” are simply not in its vocabulary.</description></item></channel></rss>