Short Article on jqknono Blogs

deepseek price increase

https://blog.jqknono.com (jqknono) — Mon, 29 Jun 2026 17:40:08 +0800

Price doubled during working hours

Share something fun, GitHub account rating

https://blog.jqknono.com (jqknono) — Sun, 28 Jun 2026 16:52:27 +0800

By default it uses the stepfun model to judge the personal data obtainable from the GitHub API, quite fun https://githubroast.dev/ #vibecodingfestival[topic]#

If Zhipu's stock price falls, where will the money flow?

https://blog.jqknono.com (jqknono) — Tue, 23 Jun 2026 13:27:30 +0800

Zhipu’s model performance is decent, but its engineering capability is limited, and subscription users can feel the service quality. The advantage of glm5.2 is rigorous thinking, at the cost of low token efficiency, leading to a higher overall price. Assuming most users do appreciate well-performing models…

opencode go supports multiple simultaneous subscriptions

https://blog.jqknono.com (jqknono) — Thu, 18 Jun 2026 15:59:15 +0800

Create multiple workspaces, each workspace can subscribe to one go. Workspaces can be created freely. No need to create multiple accounts, unless to take advantage of the $5 deal.

What new job opportunities will emerge

https://blog.jqknono.com (jqknono) — Mon, 15 Jun 2026 13:05:33 +0800

AI is surging in; let’s prepare for the future

github copilot's route choice

https://blog.jqknono.com (jqknono) — Thu, 04 Jun 2026 13:24:05 +0800

From February to July last year, copilot was freely usable in vscode insider. During this period, I witnessed the gradual decline of copilot’s agent capabilities. Hard to imagine, the first month preview of copilot was actually…

Those worried about being laid off should use AI more

https://blog.jqknono.com (jqknono) — Thu, 04 Jun 2026 12:58:14 +0800

Over the past year and a half, some companies overestimated the role of AI and began layoffs. As time went on, companies gradually realized that AI is not as smart or cheap as expected, and began to reduce AI token consumption and slow down layoffs. A very important reason is that AI…

Xiaomi API ranks among the top in LLM cost-performance

https://blog.jqknono.com (jqknono) — Thu, 28 May 2026 21:32:27 +0800

Previously posted criticism that mimo-2.5-pro’s performance couldn’t justify its pricing. Its performance really can’t be compared to gpt5.x and opus4.x. It’s not that I wanted to compare them, but Xiaomi positioned them as competitors, so I pointed out the obvious gap…

Moderate forgetting benefits model performance

https://blog.jqknono.com (jqknono) — Thu, 21 May 2026 14:32:35 +0800

The GPT-5 series has a high recall rate and can achieve very rigorous logic, making it excellent for debugging. At the same time, it can promptly detect contradictions in the context, offering a unique experience among current models. But recently, in my personal reverse engineering project, I found that GPT…

Does AI-written code have fewer or more bugs

https://blog.jqknono.com (jqknono) — Wed, 20 May 2026 16:07:44 +0800

AI writes code so fast that bugs per line are surely lower, but lines of code explode, and requirements we used to skip get cranked out, so bugs keep growing. Also, AI is unbeatable at finding others’ bugs, surfacing hidden ones…