惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - 叶小钗
D
Darknet – Hacking Tools, Hacker News & Cyber Security
S
SegmentFault 最新的问题
博客园 - 三生石上(FineUI控件)
雷峰网
雷峰网
WordPress大学
WordPress大学
有赞技术团队
有赞技术团队
博客园 - 【当耐特】
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
V
V2EX
V
Visual Studio Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
博客园 - 聂微东
P
Proofpoint News Feed
Last Week in AI
Last Week in AI
U
Unit 42
W
WeLiveSecurity
博客园 - Franky
Recent Announcements
Recent Announcements
Hacker News - Newest:
Hacker News - Newest: "LLM"
Attack and Defense Labs
Attack and Defense Labs
月光博客
月光博客
The Cloudflare Blog
Spread Privacy
Spread Privacy
腾讯CDC
P
Privacy International News Feed
N
News and Events Feed by Topic
AWS News Blog
AWS News Blog
NISL@THU
NISL@THU
T
Troy Hunt's Blog
小众软件
小众软件
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
Microsoft Security Blog
Microsoft Security Blog
L
Lohrmann on Cybersecurity
Webroot Blog
Webroot Blog
Y
Y Combinator Blog
量子位
P
Palo Alto Networks Blog
N
News and Events Feed by Topic
V
Vulnerabilities – Threatpost
K
Kaspersky official blog
IT之家
IT之家
T
Threat Research - Cisco Blogs
Cloudbric
Cloudbric
云风的 BLOG
云风的 BLOG
C
Check Point Blog
Blog — PlanetScale
Blog — PlanetScale
爱范儿
爱范儿
G
Google Developers Blog
S
Secure Thoughts

Benson's blog

Enjoy life Internship AI on academic research How AI Will Change the Mobile Ecosystem Look ahead Goodbye 2025 Hacker News to Kindle Another project How to imporve english Introduction of Fraud detection PopTranslate Last day in netease Gemini-cli LLM Post-Training experience Papers I readed recently about LLM application Difference between LLMs and traditional computer technology GRPO Weekly-#26 AI Application Weekly-#25 AI infra and application Weekly-#24 First week as LLM inference engineer Weekly-#23 seeking job Weekly-#22 2025 New Year AutoSwitch Translate Goodbye 2024 Weekly-#20 Breaking of glass Cross Entropy Loss of Triton Weekly-#18 Cross Entropy Loss of Triton Weekly-#17 Triton Puzzles Weekly-#16 AutoBuilder Weekly-#15 Starting of tanble tennis Weekly-#14 Accident in life Weekly-#13 Trying of xiaohongshu Weekly-#12 summary of LLM acceleration Outline of LLM acceleration Weekly-#11 Copilot-type products Weekly-#10 Preparation for next journey Weekly-#9 Startup of YouTube Notes of flash-attention How to learn knowledge in new fields? Weekly-#8 Start Reading Notes of LoRA Acceleration of LLM - Matrix Multiplication Weekly-#8 Summary for two month Weekly-#7 Staying home Weekly-#6 Cost of PopTranslate Weekly-#5 Updating of PopTranslate Validated example of LLM acceleration Weekly-#4 First insight of LLM accelerate Weekly-#3 PopTranslate Weekly-#2 The fail of first product Weekly-#1 First week of indie develop slack迁移discord 雅思备考 2024Q3 中文博客合集 English Diary in May 五一游记 开始休假 离职前的状态 2024-01-01 duckdb 看懂的第一个PR learning english in October learning english in September learning english in August top hack news 收集 大模型调研 自动驾驶的小玩具 旅游 扬州+苏州 small talk of learning english 新年新气象-碎碎念 刷剧 感染新冠 强化学习简介 神经网络解释性 全局的模型无关解释方法合集 社区发现算法概览 图神经网络入门(GNN) 我的第一款 iOS APP AtCoder Beginner Contest 268 人的信息输入方式对比 重叠社区检测 人穷极一生到底在追求什么 重拾生活规划 社区发现算法 - Louvain 《幸福的方法》 读《人类简史》有感 妙峰山骑行 黑客帝国 特征交互 特征工程 累计局部效应图 模型解释性-PDP 模型解释性 Web3 入门科普 总结 2022.4 孪生网络做 query 相似度任务 学习 2022.4 Imagen DeBERTa 读论文 用CNN做query相似度任务
Better idea between Copilot-typed and CLI-typed assistant
Benson · 2025-08-12 · via Benson's blog

Copilot-typed

GitHub Copilot, cursor, GPT-codex, winsurf, trae are representative products of Copilot-typed tools, their function is to help users complete code automatically when necessary. Of course, they provide interactive conversation for users with code as content, which is common feature. This is the direct usage intruction in coding field when LLM appears.

CLI-typed

Claude-code is the first CLI-typed coding assistant, after Gemini-CLI join the wars among CLI-typed coding assistants, cursor-CLI also was published on 8th August. CLI-typed tools are the representative products in vibe coding era, which means people can release themself from editors, What they only need to do is talking with LM and express their thoughts and opinions.

I think the step from Copilot-typed to CLI-typed(vibe coding) is too big to be workable, LLM cannot transfer an idea or demand into product by himself.

The main disadvantages of CLI-typed (vibe coding) is that LLM cannot solve complex projects because it’s not good at designing the solution. but developers are good at that, especially for junior developers. It’s not necessary to use LLM to solve all tasks.

Better tool

A better product should provide more space for junior developers to express their thought of design, and also provide more control space for users, some users really like the feeling of controlling and enjoy that, this also can help LLM program better code because the instrction is more clear.

More specifically, I think develpers can design their project in any depth from generality to details by the new ideal tool, and LLM can program code based on the design from developers.

In additon, there’re more advantages in this way.

  1. Designing of developers could be seen as ideal documentation of project
  2. It’s easy to save the checkpoint of the project in the process of developing.
  3. Developers are not probably mad for multi-round conversations.

Maybe this can be solved based on CLI-typed tools, but I’m not sure how to proceed in detail.

This post is licensed under CC BY 4.0 by the author.