vibecoding
I completed my 8th successful “vibe coded” project over the weekend and I’m SO excited about it!
Check out my blog post: Vibe Coded: AI Who’s Who
https://www.speedofcreativity.org/2025/11/17/vibe-coded-ai-whos-who/
Eternal November - the new influx of users, and why it's way better than the last one https://lobste.rs/s/zmilsd #culture #programming #vibecoding
https://sfconservancy.org/blog/2026/apr/15/eternal-november-generative-ai-llm/
Gemini 3 Pro 的前端設計根本好屌 !
其他那些大模型是怎樣 聽不懂人話嘛
動不動降智服務降級
#vibecoding #augment #ai #gemini3pro #developerlife
Gemini 3 Pro 手搓美美前端 ✨
我用 Gemini 3 Pro 手搓了一個美美的電子書前端,實在是泰酷了 🚀
⚡️
Built a gorgeous eBook frontend from scratch with Gemini 3 Pro — it’s insanely cool. 😎
Gemini 3 Proでめっちゃいい感じの電子書籍フロントエンドを爆速で作った。最高すぎる! 🙌
#vibecoding #augment #gemini3pro
#frontend #webdev #indiedev #coding #programming #ebook
#前端 #網頁開發 #個人開發 #獨立開發 #電子書
#プログラミング #個人開発 #ウェブデザイン #フロントエンド #電子書籍 #ジェミニ
Representation-Free Editing https://lobste.rs/s/7k9ota #editors #vibecoding
https://alperenkeles.com/posts/representation-free-editing/
Engineering judgement and the Claude Code paradox https://lobste.rs/s/hrk9st #practices #vibecoding
https://deadsimpletech.com/blog/engineering-judgement-claude-paradox
The Boy That Cried Mythos: Verification is Collapsing Trust in Anthropic https://lobste.rs/s/ttvlyt #security #vibecoding
https://www.flyingpenguin.com/the-boy-that-cried-mythos-verification-is-collapsing-trust-in-anthropic/
Mathematics in the Library of Babel https://lobste.rs/s/5wgwbz #math #vibecoding
https://www.daniellitt.com/blog/2026/2/20/mathematics-in-the-library-of-babel
I Let Claude Opus Write a Chrome Exploit: The Next Model (Mythos?) Won't Need My Help? https://lobste.rs/s/xkxbq3 #security #vibecoding
https://www.hacktron.ai/blog/i-let-claude-opus-to-write-me-a-chrome-exploit
SCTPhantom: An 18-Year-Old SCTP ASCONF Transport Use-After-Free https://lobste.rs/s/wdnet3 #linux #security #vibecoding
https://matrix.tencent.com/en/2026/08/06/sctphantom-CVE-2026-64564
The Future of Everything is Lies, I Guess: Where Do We Go From Here? https://lobste.rs/s/yhbjpt #vibecoding
https://aphyr.com/posts/420-the-future-of-everything-is-lies-i-guess-where-do-we-go-from-here
Automatic Programming Should Be More Like SQL https://lobste.rs/s/oh7zna #formalmethods #plt #vibecoding
https://stng.substack.com/p/automatic-programming-should-be-more
Robot comment classifier https://lobste.rs/s/ilfiqa #ai #practices #vibecoding
https://entropicthoughts.com/ai-comment-classifier
Building an Unverified Compiler with Agents https://lobste.rs/s/fkxdc8 #formalmethods #plt #vibecoding
https://www.basis.ai/blog/verified-compiler/
The age of fast food https://lobste.rs/s/imuls4 #vibecoding
https://www.abareplace.com/blog/ai_fastfood/
Ready for the revolution https://lobste.rs/s/punchs #rant #vibecoding
https://coyotetracks.org/blog/ready-for-revolution/
Collaborative Autoresearch on a Peer-to-Peer Network https://lobste.rs/s/fsryww #distributed #vibecoding
https://community.computer
You Need AI That Reduces Maintenance Costs https://lobste.rs/s/fy4spr #vibecoding
https://www.jamesshore.com/v2/blog/2026/you-need-ai-that-reduces-your-maintenance-costs
zmx - run local code agents on remote machines https://lobste.rs/s/oozbdu #vibecoding
https://bower.sh/zmx-ai-portal
Check out the recorded video version of my December 26th presentation, “Stories About AI” at Meadowlark Hills Retirement Community! On Substack:
https://wfryer.substack.com/p/stories-about-ai-december-2025
On YouTube: https://youtu.be/zY1dcBRTZwg?si=jvgDfLGFP3O0LP_3
More ways to learn with and connect with me (Wes Fryer) are on:
https://wesfryer.com/after
#AI #MediaLit #MediaLiteracy #ethics #VibeCoding #VibeCode #edtech #ChatGPT #Gemini #NanoBanana
Discourse is Not Going Closed Source via @hongminhee https://lobste.rs/s/ku8hlz #security #vibecoding
https://blog.discourse.org/2026/04/discourse-is-not-going-closed-source/
The CTF scene is dead https://lobste.rs/s/duyp69 #security #vibecoding
https://kabir.au/blog/the-ctf-scene-is-dead
这一周试了一下更多 #vibecoding 。
首先所有的coding agent都支持自定义模型,包括连接到本地模型,加上agent其实是本地跑的+开源的,所以只要确保模型用的是自己部署的,就能确保数据的安全性,不过自用的话问题不大。
如果是自用考虑性价比:
- 那么 #codex 用chatgpt plus订阅是最好的,量很大,而且效果也不错,大概8分,但是基于CLI,交互差一些。
如果纯粹从效果角度出发:
- #cursor (每月20USD,但是限制用量也到20+USD,超了就只能用那种mini模型),交互满分,性能9分。
- google #antigravity (用google的ai订阅,限制用量暂时没试过,free tier的用量比较低,写前端目前最强10分,别的差一些,可能是gemini3pro的特性,一个重大交互升级是能自动用浏览器看前端页面,然后模型读取前端截图来提升前端设计效果,写后端效果一般),交互和curosr一个水平也是满分,写后端的性能综合下来可能是7分。
- #claude code(每月20USD,但是注意在国内用如果IP地址泄露可能导致封号),CLI简陋的交互但是比codex好一点点,总体性能是很强的,应该是和cursor一个水平9分。
- #opencode (开源拖拉机,其中想说的是#oh-my-opencode ,拥有这个社区激进的多智能体设计),CLI交互比御三家的cli强很多,但是还是达不到IDE GUI的水平,总体性能如果能用上opus这种sota模型,基本上和cursor一个水平甚至更强(9分),考虑到多智能体一直写,可以做到无托管自己写自己debug一小时。缺点是吃的token比较多,token性价比低。
另外的:
- github #copilot :设计的不太好,好像上下文限制也较大,主要优势是如果有github教育认证就能一直白嫖订阅,总体性能不及格(5分)。
- jetbrains #junie :给JB IDE用的coding agent,一开始出的时候试过,基本出于比较糟糕的状态(2分),和模型无关,纯粹是本身设计问题,不知道现在怎么样了。