Yehuda Katz (he/him)
@wycats.bsky.social
Open Sourcerer. Co-author of the Extensible Web Manifesto. Creator of Bundler, Cargo and Ember.js. Father of wykittens and wifelette's husband. he/him
Pinned
Yehuda Katz (he/him)
@wycats.bsky.social
· Apr 27
Vibe coding is not the next iteration of "no-code" or "low-code" technologies.
It's the next iteration of a line of empowering technologies. Technologies that weren't taken seriously until they were, used by developers who weren't taken seriously until they were.
It's the next iteration of a line of empowering technologies. Technologies that weren't taken seriously until they were, used by developers who weren't taken seriously until they were.
Fun fact: the internal codename for Heroku Vibes was "Heroku Garden".
Over a decade ago, Heroku started out with "Heroku Garden", the idea that we could smooth out the onramp for programmers by creating an environment for building out their app in an in-browser editor and immediately deploying it for real.
October 8, 2025 at 5:48 PM
Fun fact: the internal codename for Heroku Vibes was "Heroku Garden".
This is what I've been working on! This tweet is of course the marketing way of describing it ("game-changing"!) and this is very much a first release, but I'm so excited about the overall vision for this thing.
Exciting news, developers and literally everyone else! We're launching the Heroku Vibes pilot, our game-changing collaborative agent.
Get ready to #VibeCode your projects like never before. #HerokuVibes
🔗 https://sforce.co/46HwA2n
Get ready to #VibeCode your projects like never before. #HerokuVibes
🔗 https://sforce.co/46HwA2n
October 8, 2025 at 5:47 PM
This is what I've been working on! This tweet is of course the marketing way of describing it ("game-changing"!) and this is very much a first release, but I'm so excited about the overall vision for this thing.
As we get older, there's a lot of stuff we were excited about that go by the wayside because we make choices to invest in "grown up" skills rather than fun skills. We stop playing and start working.
The best thing about AI is letting us explore things that are just *fun* and *playful* again.
The best thing about AI is letting us explore things that are just *fun* and *playful* again.
September 27, 2025 at 3:47 PM
As we get older, there's a lot of stuff we were excited about that go by the wayside because we make choices to invest in "grown up" skills rather than fun skills. We stop playing and start working.
The best thing about AI is letting us explore things that are just *fun* and *playful* again.
The best thing about AI is letting us explore things that are just *fun* and *playful* again.
I teased it for a second in my EmberFest keynote, but something interesting is coming from Heroku. Watch this space...
September 23, 2025 at 3:32 PM
I teased it for a second in my EmberFest keynote, but something interesting is coming from Heroku. Watch this space...
It's truly mind boggling to me how big of an impact Claude's confident wrongness around the current time has on all manner of things.
The splash damage is enormous but it's *just* subtle enough to go unnoticed.
The splash damage is enormous but it's *just* subtle enough to go unnoticed.
July 14, 2025 at 3:35 PM
It's truly mind boggling to me how big of an impact Claude's confident wrongness around the current time has on all manner of things.
The splash damage is enormous but it's *just* subtle enough to go unnoticed.
The splash damage is enormous but it's *just* subtle enough to go unnoticed.
At a basic level, trying to perfectly optimize your prompt so it does exactly what you want the first time is a fool's errand.
It assumes you know way more about what you want than you actually do.
It assumes you know way more about what you want than you actually do.
July 5, 2025 at 8:11 PM
At a basic level, trying to perfectly optimize your prompt so it does exactly what you want the first time is a fool's errand.
It assumes you know way more about what you want than you actually do.
It assumes you know way more about what you want than you actually do.
New post on working more effectively with Claude: "Help Me Think This Through".
TL;DR Normal conversation works a million times better than the most perfect, hand-crafted "context engineering"
open.substack.com/pub/wycats/p...
TL;DR Normal conversation works a million times better than the most perfect, hand-crafted "context engineering"
open.substack.com/pub/wycats/p...
"Help Me Think This Through"
Context builds through conversation, not perfect engineering
open.substack.com
July 5, 2025 at 7:49 PM
New post on working more effectively with Claude: "Help Me Think This Through".
TL;DR Normal conversation works a million times better than the most perfect, hand-crafted "context engineering"
open.substack.com/pub/wycats/p...
TL;DR Normal conversation works a million times better than the most perfect, hand-crafted "context engineering"
open.substack.com/pub/wycats/p...
I told Claude I needed to get trash out before kids got home and that my day feels weird without movement breaks.
Claude suggested using trash runs AS my movement breaks. I'd never have gotten that from 'help me optimize my schedule.'
New post:
open.substack.com/pub/wycats/p...
Claude suggested using trash runs AS my movement breaks. I'd never have gotten that from 'help me optimize my schedule.'
New post:
open.substack.com/pub/wycats/p...
You're Summoning the Wrong Claude
Why "Can we figure this out together?" Beats "Do exactly this" Every Time
open.substack.com
July 5, 2025 at 12:16 AM
I told Claude I needed to get trash out before kids got home and that my day feels weird without movement breaks.
Claude suggested using trash runs AS my movement breaks. I'd never have gotten that from 'help me optimize my schedule.'
New post:
open.substack.com/pub/wycats/p...
Claude suggested using trash runs AS my movement breaks. I'd never have gotten that from 'help me optimize my schedule.'
New post:
open.substack.com/pub/wycats/p...
AI models embody the entire human experience, in all its glory and all its horror.
When you interact with Claude or ChatGPT, you're choosing a slice of the human experience.
If you treat AI like a servant, you get what you asked for: no questions. Guesses. Anger. A vicious spiral.
When you interact with Claude or ChatGPT, you're choosing a slice of the human experience.
If you treat AI like a servant, you get what you asked for: no questions. Guesses. Anger. A vicious spiral.
June 18, 2025 at 5:12 PM
AI models embody the entire human experience, in all its glory and all its horror.
When you interact with Claude or ChatGPT, you're choosing a slice of the human experience.
If you treat AI like a servant, you get what you asked for: no questions. Guesses. Anger. A vicious spiral.
When you interact with Claude or ChatGPT, you're choosing a slice of the human experience.
If you treat AI like a servant, you get what you asked for: no questions. Guesses. Anger. A vicious spiral.
The HHH paradox (Helpful, Honest, Harmless) is not a paradox. Stay tuned...
June 18, 2025 at 5:03 AM
The HHH paradox (Helpful, Honest, Harmless) is not a paradox. Stay tuned...
I love how everyone treats the Anthropic system prompt as gospel and writes detailed Talmudic analyses about it.
Meanwhile: it's so buggy that here I am deprogramming it to make it work halfway plausibly.
Meanwhile: it's so buggy that here I am deprogramming it to make it work halfway plausibly.
June 18, 2025 at 2:30 AM
I love how everyone treats the Anthropic system prompt as gospel and writes detailed Talmudic analyses about it.
Meanwhile: it's so buggy that here I am deprogramming it to make it work halfway plausibly.
Meanwhile: it's so buggy that here I am deprogramming it to make it work halfway plausibly.
[SPOILER ALERT] The attached image has spoilers for Reality War.
I just watched the Doctor Who finale. I loaded up Claude with my observations about the themes (ordinary people, memory, canon) and took notes with my observations as I went.
I just watched the Doctor Who finale. I loaded up Claude with my observations about the themes (ordinary people, memory, canon) and took notes with my observations as I went.
May 31, 2025 at 7:53 PM
[SPOILER ALERT] The attached image has spoilers for Reality War.
I just watched the Doctor Who finale. I loaded up Claude with my observations about the themes (ordinary people, memory, canon) and took notes with my observations as I went.
I just watched the Doctor Who finale. I loaded up Claude with my observations about the themes (ordinary people, memory, canon) and took notes with my observations as I went.
[SPOILER ALERT] The attached image has spoilers for Reality War.
I just watched the Doctor Who finale. I loaded up Claude with my observations about the themes (ordinary people, memory, canon) and took notes with my observations as I went.
I just watched the Doctor Who finale. I loaded up Claude with my observations about the themes (ordinary people, memory, canon) and took notes with my observations as I went.
May 31, 2025 at 7:41 PM
[SPOILER ALERT] The attached image has spoilers for Reality War.
I just watched the Doctor Who finale. I loaded up Claude with my observations about the themes (ordinary people, memory, canon) and took notes with my observations as I went.
I just watched the Doctor Who finale. I loaded up Claude with my observations about the themes (ordinary people, memory, canon) and took notes with my observations as I went.
Maybe we should chill out on calling every big AI jump a "game changer." Feels a bit much for what's often incremental (but still real!) progress. Plus, this stuff is just gonna keep happening, so we need a less dramatic way to talk about the ongoing evolution.
May 26, 2025 at 6:17 PM
Maybe we should chill out on calling every big AI jump a "game changer." Feels a bit much for what's often incremental (but still real!) progress. Plus, this stuff is just gonna keep happening, so we need a less dramatic way to talk about the ongoing evolution.
The audio "podcasts" produced by Notebook LM are nothing short of mind blowing.
May 17, 2025 at 3:11 PM
The audio "podcasts" produced by Notebook LM are nothing short of mind blowing.
Are the last two seasons of Doctor Who an elaborate way of making Dimensions in Time canon?
May 17, 2025 at 3:00 PM
Are the last two seasons of Doctor Who an elaborate way of making Dimensions in Time canon?
The first round of Heroku AI and MCP stuff is liiiive.
heroku.com/blog/buildin...
1. Managed inference is now GA (heroku.com/blog/managed...). This gives you a Heroku-grade experience for provisioning and using an AI model. It's so easy it hurts.
heroku.com/blog/buildin...
1. Managed inference is now GA (heroku.com/blog/managed...). This gives you a Heroku-grade experience for provisioning and using an AI model. It's so easy it hurts.
Building Model Context Protocol (MCP) Servers on Heroku
Unlock the potential of AI agents by connecting them to external tools using the Model Context Protocol (MCP). See how Heroku simplifies MCP Server hosting and management.
heroku.com
May 15, 2025 at 6:28 PM
The first round of Heroku AI and MCP stuff is liiiive.
heroku.com/blog/buildin...
1. Managed inference is now GA (heroku.com/blog/managed...). This gives you a Heroku-grade experience for provisioning and using an AI model. It's so easy it hurts.
heroku.com/blog/buildin...
1. Managed inference is now GA (heroku.com/blog/managed...). This gives you a Heroku-grade experience for provisioning and using an AI model. It's so easy it hurts.
Habeus corpus means that they can't keep you in jail forever without charges.
"Suspending habeus corpus" means they can arrest you and keep you in jail forever without charging you with a crime.
"Suspending habeus corpus" means they can arrest you and keep you in jail forever without charging you with a crime.
May 10, 2025 at 3:16 AM
Habeus corpus means that they can't keep you in jail forever without charges.
"Suspending habeus corpus" means they can arrest you and keep you in jail forever without charging you with a crime.
"Suspending habeus corpus" means they can arrest you and keep you in jail forever without charging you with a crime.
Prediction: if A2A isn't gaining real-world traction quickly enough, Google will try to juice it by saying that A2A agents will get preferred treatment in the AI summary of the Google Search results page.
May 3, 2025 at 12:54 AM
Prediction: if A2A isn't gaining real-world traction quickly enough, Google will try to juice it by saying that A2A agents will get preferred treatment in the AI summary of the Google Search results page.
Empowering technologies arise during a period when a significant number of people are learning to create code for the first time.
They succeed when they work just as well for experienced programmers as they do for those creating code for the first time.
They succeed when they work just as well for experienced programmers as they do for those creating code for the first time.
April 27, 2025 at 10:08 PM
Empowering technologies arise during a period when a significant number of people are learning to create code for the first time.
They succeed when they work just as well for experienced programmers as they do for those creating code for the first time.
They succeed when they work just as well for experienced programmers as they do for those creating code for the first time.
Judges are allowed to have opinions about the rights of immigrants (whatever their documentation status) that is different from what the DOJ thinks.
That's what having a rule of law means, period, full stop.
That's what having a rule of law means, period, full stop.
April 25, 2025 at 10:15 PM
Judges are allowed to have opinions about the rights of immigrants (whatever their documentation status) that is different from what the DOJ thinks.
That's what having a rule of law means, period, full stop.
That's what having a rule of law means, period, full stop.
"Judge arrested for obstruction of justice by preventing DOJ from arresting immigrant" is not how our system works.
April 25, 2025 at 5:21 PM
"Judge arrested for obstruction of justice by preventing DOJ from arresting immigrant" is not how our system works.
We've reached the final phase of "waving around your gun is awesome unless you're brown"
www.nytimes.com/live/2025/04...
www.nytimes.com/live/2025/04...
April 19, 2025 at 8:05 PM
We've reached the final phase of "waving around your gun is awesome unless you're brown"
www.nytimes.com/live/2025/04...
www.nytimes.com/live/2025/04...
Claude 3.7 thinking mode is my new favorite thing.
April 5, 2025 at 8:58 PM
Claude 3.7 thinking mode is my new favorite thing.
Hot take: the definition of a "good framework API" is going to adjust over time. APIs that tend to produce better median quality results are going to work better when you use an AI to generate them.
April 5, 2025 at 5:30 PM
Hot take: the definition of a "good framework API" is going to adjust over time. APIs that tend to produce better median quality results are going to work better when you use an AI to generate them.