Kevin Kern
@kevinkern.dev
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
📓 Building instructa.ai Academy
Curated Ai Prompts instructa.ai/en/ai-prompts
🇺🇦 Raised 20k for UA
👨💻 coder & design
Website: kevinkern.dev
📍 Vienna, Austria
TIL: ChatGPT can create simple sound files for you (I was looking for free sounds for codex-1up).
November 12, 2025 at 7:32 PM
TIL: ChatGPT can create simple sound files for you (I was looking for free sounds for codex-1up).
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
- 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
November 11, 2025 at 7:31 PM
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
- 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
in the next version of codex-1up, a new fast guided setup.
November 10, 2025 at 10:19 PM
in the next version of codex-1up, a new fast guided setup.
A new stealth model, polaris-alpha, has appeared on openrouter. Time to give it a try.
November 9, 2025 at 12:14 AM
A new stealth model, polaris-alpha, has appeared on openrouter. Time to give it a try.
My earlier take is deprecated.
November 7, 2025 at 1:19 PM
My earlier take is deprecated.
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.
November 6, 2025 at 9:10 AM
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.
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.
In my case I use a slash command with gpt-5. Usually you find some flaws in the final implementation.
November 6, 2025 at 2:31 AM
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.
In my case I use a slash command with gpt-5. Usually you find some flaws in the final implementation.
Finally I found a way to 10x codex! Sound on! 🔊
November 5, 2025 at 6:43 AM
Finally I found a way to 10x codex! Sound on! 🔊
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 🧵
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 🧵
November 3, 2025 at 1:29 PM
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 🧵
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 🧵
This script plays a sound when Codex finishes your task.
October 31, 2025 at 7:42 AM
This script plays a sound when Codex finishes your task.
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.
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.
October 30, 2025 at 7:24 PM
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.
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.
I've put together a collection of slash commands I use with Codex and Cursor. ⚡
Link in the comments
Link in the comments
October 14, 2025 at 3:06 PM
I've put together a collection of slash commands I use with Codex and Cursor. ⚡
Link in the comments
Link in the comments
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.
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.
October 13, 2025 at 10:18 AM
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.
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.
Cheetah is such a beast model. refactor to a monorepo, including smoke tests & CLI updates, in just a few minutes.
October 12, 2025 at 4:38 PM
Cheetah is such a beast model. refactor to a monorepo, including smoke tests & CLI updates, in just a few minutes.
Codex CLI Model selector looks clean now.
It seems that the configs for model_reasoning_effort (low, medium, high) are still available.
It seems that the configs for model_reasoning_effort (low, medium, high) are still available.
October 8, 2025 at 11:02 AM
Codex CLI Model selector looks clean now.
It seems that the configs for model_reasoning_effort (low, medium, high) are still available.
It seems that the configs for model_reasoning_effort (low, medium, high) are still available.
Look, the final boss spawned in Cursor.
October 8, 2025 at 10:35 AM
Look, the final boss spawned in Cursor.
A bit harsh but this is how i treat Claude plans when I hand them over to codex for implementation.
October 7, 2025 at 5:27 PM
A bit harsh but this is how i treat Claude plans when I hand them over to codex for implementation.
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.
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.
October 7, 2025 at 4:12 PM
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.
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.
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.
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.
October 7, 2025 at 1:48 PM
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.
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.
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
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
October 2, 2025 at 2:44 PM
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
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
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.
It's really cool that it finally made it into the new Cursor Version.
October 1, 2025 at 3:53 PM
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.
It's really cool that it finally made it into the new Cursor Version.
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.
🧵👇
1. First, I'm using Iconify, which is a developer friendly icon set framework.
🧵👇
September 30, 2025 at 9:54 PM
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.
🧵👇
1. First, I'm using Iconify, which is a developer friendly icon set framework.
🧵👇
New look, clearer Cursor.
September 30, 2025 at 7:21 PM
New look, clearer Cursor.
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.
Add Terraform, Ansible, Dokku and manage it with your own CLI.
September 30, 2025 at 1:07 PM
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.
Add Terraform, Ansible, Dokku and manage it with your own CLI.
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.
But Anthropic has never released a stealth model, and xAI published grok-code-fast-1 (sonic) recently.
September 22, 2025 at 8:57 PM
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.
But Anthropic has never released a stealth model, and xAI published grok-code-fast-1 (sonic) recently.