Sign in

Kevin Kern

@kevinkern.dev
188 followers 448 following 677 posts

Teaching & building AI apps to reduce the workload 📓 Building instructa.ai Academy Curated Ai Prompts instructa.ai/en/ai-prompts 🇺🇦 Raised 20k for UA 👨‍💻 coder & design Website: kevinkern.dev 📍 Vienna, Austria

PostsRepliesMedia
Kevin Kern @kevinkern.dev · 30/01/2026
put all my shell scripts in one repo. Feel free to use them. github.com/regenrek/sh...
github.com
GitHub - regenrek/shellrig: My own shell scripts I use daily
My own shell scripts I use daily. Contribute to regenrek/shellrig development by creating an account on GitHub.
010
Kevin Kern @kevinkern.dev · 29/01/2026
Over the last few weeks I've been moving away from a few cloud providers. I've wanted to do this for a while, not because they're bad, but because a lot of them are built for bigger teams/enterprise and I don't need most of those features. Slack → RocketChat Pandadoc → Docuseal
120
Kevin Kern @kevinkern.dev · 14/01/2026
Jira is so slow and bloated that it was worth to spend some time to build my own desktop app (that syncs incoming issues) How? 1. wrote a spec in gpt-5.2 2. paste spec to aistudio (Gemini 3 Pro) for frontend 3. paste spec to gpt pro for initial mvp backend code
110
Kevin Kern @kevinkern.dev · 05/01/2026
That's another reason why GPT-5.2 reviews Opus-4.5. great at rushing through the codebase and identifying mistakes. At the same time, it's sloppy and sometimes stops halfway instead of following through. still overpromises, but with gpt-5.2 oversight we consistently land on high quality results.
100
Kevin Kern @kevinkern.dev · 03/01/2026
Since Codex is taking forever for larger codebases, I split my tasks across to 5-8 agents. the important part is that it's split by domain so you don't overwrite things. But Codex is pretty good at recognizing others' work and stops or asks if it should proceed.
110
Kevin Kern @kevinkern.dev · 21/11/2025
was playing around with Codefetch and oracle to gather context and send hard tasks to GPT-5.1 Pro. here's a slash command I ended up with.
110
Kevin Kern @kevinkern.dev · 21/11/2025
GPT 5.1 Pro dropped
010
Kevin Kern @kevinkern.dev · 20/11/2025
little annoying that Codex removes things "for good". I'm telling it this from now on.
010
Kevin Kern @kevinkern.dev · 20/11/2025
Just released Oplink.⚡️It combines multiple MCP servers into unified workflows.
100
Kevin Kern @kevinkern.dev · 20/11/2025
Nice addon for codex. Oracle sends your hard tasks to gpt 5 pro. Tip: You can pair it with codefetch to set up the context first.
000
Kevin Kern @kevinkern.dev · 12/11/2025
TIL: ChatGPT can create simple sound files for you (I was looking for free sounds for codex-1up).
010
Kevin Kern @kevinkern.dev · 11/11/2025
A fresh codex-1up update is out. - Quick install "npm install -g codex-1up" - Add custom sounds when a task is finished - Guided setup (easy for beginners) - Lot of cleanup, improvements - New updated profiles to start quickly
100
Kevin Kern @kevinkern.dev · 10/11/2025
in the next version of codex-1up, a new fast guided setup.
000
Kevin Kern @kevinkern.dev · 09/11/2025
A new stealth model, polaris-alpha, has appeared on openrouter. Time to give it a try.
000
Kevin Kern @kevinkern.dev · 07/11/2025
My earlier take is deprecated.
100
Kevin Kern @kevinkern.dev · 06/11/2025
I've updated today the tanstack starter project + agent rules. You can build now quickly web apps with one the best web dev stack available.
000
Kevin Kern @kevinkern.dev · 06/11/2025
f you use composer-1 in cursor for coding, it's helpful to run a quick /code-review to identify any code smells. In my case I use a slash command with gpt-5. Usually you find some flaws in the final implementation.
100
Kevin Kern @kevinkern.dev · 05/11/2025
Finally I found a way to 10x codex! Sound on! 🔊
000
Kevin Kern @kevinkern.dev · 03/11/2025
Cursor 2.0 update and their new agentic model "composer-1-alpha" I've been testing it for a few days and have put together a full summary in the thread below. Click to see whats new 🧵
110
Kevin Kern @kevinkern.dev · 31/10/2025
This script plays a sound when Codex finishes your task.
100
Kevin Kern @kevinkern.dev · 30/10/2025
If you work in a larger company and your team uses Jira, I can recommend the "mcp-atlassian" MCP. It's probably the only MCP I'm currently using. I fetch all stories for a given epic in markdown, including the specification stored in confluence and export the figma screens.
100
Kevin Kern @kevinkern.dev · 14/10/2025
I've put together a collection of slash commands I use with Codex and Cursor. ⚡ Link in the comments
100
Kevin Kern @kevinkern.dev · 13/10/2025
The new Plan mode in Cursor is well thought out. It builds on the existing task lists, showing they iterate on what’s already there and bring features together instead of shipping separate ones. I like that approach.
000
Kevin Kern @kevinkern.dev · 12/10/2025
Cheetah is such a beast model. refactor to a monorepo, including smoke tests & CLI updates, in just a few minutes.
100
Kevin Kern @kevinkern.dev · 08/10/2025
Codex CLI Model selector looks clean now. It seems that the configs for model_reasoning_effort (low, medium, high) are still available.
100
Kevin Kern @kevinkern.dev · 08/10/2025
Look, the final boss spawned in Cursor.
100
Kevin Kern @kevinkern.dev · 07/10/2025
A bit harsh but this is how i treat Claude plans when I hand them over to codex for implementation.
000
Kevin Kern @kevinkern.dev · 07/10/2025
Loving the speed of the cheetah model in Cursor! Still, it's not flawless. It took 5 iterations to get green light from Codex to implement the plan. But first impressions are positive. Worth testing further within my workflow as a fast Q&A, planning, and peer review model alongside gpt Codex.
000
Kevin Kern @kevinkern.dev · 07/10/2025
The new "cheetah" stealth model is the first model that is not free. Which probably means it comes from one of the major AI labs. If we follow the usual release loop of models, it fits for Gemini 3. And since it’s pretty fast, it feels more like a Flash model than the Pro one.
100
Kevin Kern @kevinkern.dev · 02/10/2025
New Cursor 1.7 update is out 1/ Agent Autocomplete for prompts 2/ Hooks to control & extend the Agent loop 3/ Team Rules set global rules in the dashboard for all projects. Bugbot now follows team rules too. 4/ Share reusable prompts via links for docs 5/ Checking Agent Status with Menubar Monitor
100
Kevin Kern @kevinkern.dev · 01/10/2025
Hacking the Agent loop with your own hooks is a feature I wished we had months ago. It's really cool that it finally made it into the new Cursor Version.
000
Kevin Kern @kevinkern.dev · 30/09/2025
When using icon libraries for AI Coding i do the following. 1. First, I'm using Iconify, which is a developer friendly icon set framework. 🧵👇
100
Kevin Kern @kevinkern.dev · 30/09/2025
New look, clearer Cursor.
100
Kevin Kern @kevinkern.dev · 30/09/2025
It takes one day with Codex CLI to build your own infra that deploys a full-stack app (TanStack Start, Postgres, S3) on a €3.29 Hetzner Server. Add Terraform, Ansible, Dokku and manage it with your own CLI.
100
Kevin Kern @kevinkern.dev · 22/09/2025
There are many rumors about what "code-supernova" is. Some say it could be another Grok model or even Claude 4.5. But Anthropic has never released a stealth model, and xAI published grok-code-fast-1 (sonic) recently.
110
Kevin Kern @kevinkern.dev · 19/09/2025
OpenAI released GPT‑5-Codex today. - Install: cargo install --git github .com/openai/codex.git --tag rust-v0.36.0 codex-cli - Adaptive thinking speed + depth: 93.7% fewer tokens on easy tasks (up to 10× faster) and 2× reasoning on the hardest
100
Kevin Kern @kevinkern.dev · 18/09/2025
To enable web search for Codex, set [tools] web_search = true
000
Kevin Kern @kevinkern.dev · 16/09/2025
Added a new special offer for Instructa AI students. 1 Month of Cursor for Free. Thanks Cursor Team!
000
Kevin Kern @kevinkern.dev · 15/09/2025
These are the AGENT rules I'm using for my project - Tanstack / react / shadcn - Cloudflare / Alchemy - Drizzle - Linting
010
Kevin Kern @kevinkern.dev · 12/09/2025
I've just released a new version of Codex CLI 1UP Link in the comment 👇
100
Kevin Kern @kevinkern.dev · 10/09/2025
These are the rules I use with Codex CLI to make code search faster and more accurate.
100
Kevin Kern @kevinkern.dev · 02/09/2025
First, use grok-code-fast-1 to find the files you need for the refactor. After that, use gpt-5 to plan and carry out the changes in Cursor. This method is faster than having gpt-5 search for context on its own. Bonus Tip: If you want to increase the quality.
110
Kevin Kern @kevinkern.dev · 22/08/2025
Using GPT-5 and Claude Opus for peer reviews is a great option when you're not sure about a code change. It feels like having a skilled developer give you a second opinion.
100
Kevin Kern @kevinkern.dev · 21/08/2025
Try to keep an eye out for the stealth models, either in Cursor/Cline (like "sonic" now) or on OpenRouter These models are preview models, but they’re often really powerful, fast, and FREE. sonic -> grok code (?) horizon-alpha/beta -> Early GPT-5 quasar -> GPT-4.1
000
Kevin Kern @kevinkern.dev · 21/08/2025
Cursor added a new stealth model called "Sonic."
000
Kevin Kern @kevinkern.dev · 19/08/2025
Here are my quick thoughts on GPT-5: (after a weekend coding) Chat GPT-5: At this point, it's like a calculator... ask, then get an answer. Pragmatic, but not very relevant for coding.
100
Kevin Kern @kevinkern.dev · 18/08/2025
Launch ChatGPT 5 with a prompt directly from your desktop. (Raycast) Press ⌘ + SPACE, select a model, and start asking. Link in the comments.
100
Kevin Kern @kevinkern.dev · 14/08/2025
Get Next.js console errors live from the browser to fix them Cursor.
100
Kevin Kern @kevinkern.dev · 13/08/2025
Here is my August Tool Stack for complex tasks and large codebases. 1. Identify a problem or task you want to solve. 2. Research, plan, and define the tech stack (GPT-5 Pro + Deep Research + GitHub). 3. Implement the task step by step using batch prompting (GPT-5 Pro).
100
Kevin Kern @kevinkern.dev · 13/08/2025
One thing I've observed with Agentic Coding and new features is backward compatibility and fallbacks. GPT-5 and Claude behave the same way.
100