Dion Almaer
@almaer.com
Bringing nuance to a knife fight 🔪, surprisingly older than @bgalbs
Past: Ajaxian, Shopify, Google, Mozilla, webOS, and more!
Past: Ajaxian, Shopify, Google, Mozilla, webOS, and more!
★ Stitching with the new Jules API
The Jules team finished off another ship week with an initial version of their API, allowing you to integrate with your friendly asynchronous squid engineer.
In this post I show how I use Stitch to design a native app that uses the new API...
The Jules team finished off another ship week with an initial version of their API, allowing you to integrate with your friendly asynchronous squid engineer.
In this post I show how I use Stitch to design a native app that uses the new API...
October 7, 2025 at 8:57 PM
★ Stitching with the new Jules API
The Jules team finished off another ship week with an initial version of their API, allowing you to integrate with your friendly asynchronous squid engineer.
In this post I show how I use Stitch to design a native app that uses the new API...
The Jules team finished off another ship week with an initial version of their API, allowing you to integrate with your friendly asynchronous squid engineer.
In this post I show how I use Stitch to design a native app that uses the new API...
Not a bad start to a Sunday… with the footy on TV and using Jules to build an iOS app that uses it’s new API… designed by Stitch.
stitch.withgoogle.com/projects/272...
stitch.withgoogle.com/projects/272...
October 5, 2025 at 7:17 PM
Not a bad start to a Sunday… with the footy on TV and using Jules to build an iOS app that uses it’s new API… designed by Stitch.
stitch.withgoogle.com/projects/272...
stitch.withgoogle.com/projects/272...
★ Pools of Extraction
I’ve started to notice some patterns in how I work on software projects. I create throwaway projects to learn from, and large repos with a bunch of ideas in. I sometimes extract targeted repos from them…
I’ve started to notice some patterns in how I work on software projects. I create throwaway projects to learn from, and large repos with a bunch of ideas in. I sometimes extract targeted repos from them…
September 23, 2025 at 9:38 PM
★ Pools of Extraction
I’ve started to notice some patterns in how I work on software projects. I create throwaway projects to learn from, and large repos with a bunch of ideas in. I sometimes extract targeted repos from them…
I’ve started to notice some patterns in how I work on software projects. I create throwaway projects to learn from, and large repos with a bunch of ideas in. I sometimes extract targeted repos from them…
✨Stitch Design Variants: A Picture Really Is Worth a Thousand Words?
We have some great Stitch updates for you today, & I posted about a couple.
At first I talk about design variants and how to use the fact that your brain can grok a lot of images very quickly...
blog.almaer.com/stitch-desig...
We have some great Stitch updates for you today, & I posted about a couple.
At first I talk about design variants and how to use the fact that your brain can grok a lot of images very quickly...
blog.almaer.com/stitch-desig...
Stitch Design Variants: A Picture Really Is Worth a Thousand Words?
My head has been in the world of code generation for the last few years. Now that I’m also thinking about design generation, I’m seeing a lot of similarities but also some fascinating d…
blog.almaer.com
September 19, 2025 at 4:48 PM
✨Stitch Design Variants: A Picture Really Is Worth a Thousand Words?
We have some great Stitch updates for you today, & I posted about a couple.
At first I talk about design variants and how to use the fact that your brain can grok a lot of images very quickly...
blog.almaer.com/stitch-desig...
We have some great Stitch updates for you today, & I posted about a couple.
At first I talk about design variants and how to use the fact that your brain can grok a lot of images very quickly...
blog.almaer.com/stitch-desig...
I’m super excited about Opal, a new experiment from Google Labs.
It has changed my habits. Instead of asking for something in an AI chat app, for some tasks I create a micro app on the fly…
developers.googleblog.com/en/introduci...
It has changed my habits. Instead of asking for something in an AI chat app, for some tasks I create a micro app on the fly…
developers.googleblog.com/en/introduci...
Introducing Opal: describe, create, and share your AI mini-apps- Google Developers Blog
Discover Opal, a new experimental tool from Google Labs, that helps you compose prompts into dynamic, multi-step mini-apps using natural language.
developers.googleblog.com
July 24, 2025 at 5:13 PM
I’m super excited about Opal, a new experiment from Google Labs.
It has changed my habits. Instead of asking for something in an AI chat app, for some tasks I create a micro app on the fly…
developers.googleblog.com/en/introduci...
It has changed my habits. Instead of asking for something in an AI chat app, for some tasks I create a micro app on the fly…
developers.googleblog.com/en/introduci...
OH “We got too many Product Managers who were good at competitive analysis but not deeply technical, so we ended up with fear based copy cat roadmaps.”
June 15, 2025 at 3:37 AM
OH “We got too many Product Managers who were good at competitive analysis but not deeply technical, so we ended up with fear based copy cat roadmaps.”
“Without the appropriate error handling, the null pointer caused the binary to crash.”
status.cloud.google.com/incidents/ow...
Cue the Rust crowd…
status.cloud.google.com/incidents/ow...
Cue the Rust crowd…
Google Cloud Service Health
status.cloud.google.com
June 15, 2025 at 3:19 AM
“Without the appropriate error handling, the null pointer caused the binary to crash.”
status.cloud.google.com/incidents/ow...
Cue the Rust crowd…
status.cloud.google.com/incidents/ow...
Cue the Rust crowd…
"no matter who you are, most of the smartest people work for someone else" — Bill Joy
We have used open source as a way to leverage this, and now we are using LLMs with massive sets of knowledge as a form of leverage.
en.wikipedia.org/wiki/Joy%27s...
We have used open source as a way to leverage this, and now we are using LLMs with massive sets of knowledge as a form of leverage.
en.wikipedia.org/wiki/Joy%27s...
Joy's law (management) - Wikipedia
en.wikipedia.org
June 9, 2025 at 9:27 PM
"no matter who you are, most of the smartest people work for someone else" — Bill Joy
We have used open source as a way to leverage this, and now we are using LLMs with massive sets of knowledge as a form of leverage.
en.wikipedia.org/wiki/Joy%27s...
We have used open source as a way to leverage this, and now we are using LLMs with massive sets of knowledge as a form of leverage.
en.wikipedia.org/wiki/Joy%27s...
I use playwright-mcp to drive the browser, but why not go directly to CDP to get full access to networking and performance as well as DOM etc?
Stefan Li wired this up with devtools/mcp! Love it!
autoconfig.io/devtools-mcp...
Stefan Li wired this up with devtools/mcp! Love it!
autoconfig.io/devtools-mcp...
Give your coding agent browser superpowers with DevTools access via MCP
Give your coding agent direct access to Chrome DevTools Protocol through MCP, enabling it to inspect, interact with, and debug web applications at runtime.
autoconfig.io
June 3, 2025 at 8:00 PM
I use playwright-mcp to drive the browser, but why not go directly to CDP to get full access to networking and performance as well as DOM etc?
Stefan Li wired this up with devtools/mcp! Love it!
autoconfig.io/devtools-mcp...
Stefan Li wired this up with devtools/mcp! Love it!
autoconfig.io/devtools-mcp...
Reposted by Dion Almaer
JVM devs, this one’s for you: Rod Johnson (Spring) just dropped an OSS agent framework.
JVM-native, Kotlin-based, and focused on agentic flows mixing LLM-prompted interactions with code and domain models.
#Java #Kotlin #AINativeDev #News #OSS
JVM-native, Kotlin-based, and focused on agentic flows mixing LLM-prompted interactions with code and domain models.
#Java #Kotlin #AINativeDev #News #OSS
May 29, 2025 at 4:05 PM
JVM devs, this one’s for you: Rod Johnson (Spring) just dropped an OSS agent framework.
JVM-native, Kotlin-based, and focused on agentic flows mixing LLM-prompted interactions with code and domain models.
#Java #Kotlin #AINativeDev #News #OSS
JVM-native, Kotlin-based, and focused on agentic flows mixing LLM-prompted interactions with code and domain models.
#Java #Kotlin #AINativeDev #News #OSS
Which group will be the AI and which the humans?
May 25, 2025 at 3:02 PM
Which group will be the AI and which the humans?
Reposted by Dion Almaer
One of the most interesting announcements at I/O got just a few seconds of airtime: Gemini Diffusion.
A diffusion-based language model that:
• Generates in parallel, not left-to-right
• Hits ~1500 tokens/sec
• Can self-correct mid-generation
Read all about it here: https://www.ainativedev.co/99j
A diffusion-based language model that:
• Generates in parallel, not left-to-right
• Hits ~1500 tokens/sec
• Can self-correct mid-generation
Read all about it here: https://www.ainativedev.co/99j
May 22, 2025 at 3:37 PM
One of the most interesting announcements at I/O got just a few seconds of airtime: Gemini Diffusion.
A diffusion-based language model that:
• Generates in parallel, not left-to-right
• Hits ~1500 tokens/sec
• Can self-correct mid-generation
Read all about it here: https://www.ainativedev.co/99j
A diffusion-based language model that:
• Generates in parallel, not left-to-right
• Hits ~1500 tokens/sec
• Can self-correct mid-generation
Read all about it here: https://www.ainativedev.co/99j
Gemini Diffusion!
I love a good zig and zag. We used to be in a world where image generation used diffusion techniques (from noise), and text used autoregresion (next token). ChatGPT added 4o image generation that went the other way and used autoregression …
I love a good zig and zag. We used to be in a world where image generation used diffusion techniques (from noise), and text used autoregresion (next token). ChatGPT added 4o image generation that went the other way and used autoregression …
May 20, 2025 at 5:37 PM
Gemini Diffusion!
I love a good zig and zag. We used to be in a world where image generation used diffusion techniques (from noise), and text used autoregresion (next token). ChatGPT added 4o image generation that went the other way and used autoregression …
I love a good zig and zag. We used to be in a world where image generation used diffusion techniques (from noise), and text used autoregresion (next token). ChatGPT added 4o image generation that went the other way and used autoregression …
en.wikipedia.org/wiki/OpenAI_...
Or wait no, it’s a CLI, oh wait no it’s a remote agent platform… and a new model family…
Or wait no, it’s a CLI, oh wait no it’s a remote agent platform… and a new model family…
OpenAI Codex - Wikipedia
en.wikipedia.org
May 16, 2025 at 8:05 PM
en.wikipedia.org/wiki/OpenAI_...
Or wait no, it’s a CLI, oh wait no it’s a remote agent platform… and a new model family…
Or wait no, it’s a CLI, oh wait no it’s a remote agent platform… and a new model family…
Reposted by Dion Almaer
AI tools multiply, and so do config files.
“This has all given birth to a plethora of rules files that we need to manage.”
Vibe-rules CLI discovers and syncs them so you can code not babysit .yaml.
Details ➜ www.ainativedev.co/nbp
#AINativeDev #DevTools #AIDevelopment #CLI
“This has all given birth to a plethora of rules files that we need to manage.”
Vibe-rules CLI discovers and syncs them so you can code not babysit .yaml.
Details ➜ www.ainativedev.co/nbp
#AINativeDev #DevTools #AIDevelopment #CLI
May 8, 2025 at 8:27 AM
AI tools multiply, and so do config files.
“This has all given birth to a plethora of rules files that we need to manage.”
Vibe-rules CLI discovers and syncs them so you can code not babysit .yaml.
Details ➜ www.ainativedev.co/nbp
#AINativeDev #DevTools #AIDevelopment #CLI
“This has all given birth to a plethora of rules files that we need to manage.”
Vibe-rules CLI discovers and syncs them so you can code not babysit .yaml.
Details ➜ www.ainativedev.co/nbp
#AINativeDev #DevTools #AIDevelopment #CLI
% parade list openai
I've been enjoying building simple tools writing a spec and having them generated.
`parade` uses Ink and Vercel's AI SDK to let me explore model names from various providers (because I am using the openai:gpt-4o type URI format in other tools).
github.com/dalmaer/parade
I've been enjoying building simple tools writing a spec and having them generated.
`parade` uses Ink and Vercel's AI SDK to let me explore model names from various providers (because I am using the openai:gpt-4o type URI format in other tools).
github.com/dalmaer/parade
May 7, 2025 at 3:54 PM
% parade list openai
I've been enjoying building simple tools writing a spec and having them generated.
`parade` uses Ink and Vercel's AI SDK to let me explore model names from various providers (because I am using the openai:gpt-4o type URI format in other tools).
github.com/dalmaer/parade
I've been enjoying building simple tools writing a spec and having them generated.
`parade` uses Ink and Vercel's AI SDK to let me explore model names from various providers (because I am using the openai:gpt-4o type URI format in other tools).
github.com/dalmaer/parade
It’s a sin that this happened to Adam. A true world class frontend engineer and a world class human. I remember being so excited when we first spoke about him joining Chrome and then talking VisBug. And he’s gone from strength to strength. What an epic own goal.
April 11, 2025 at 6:25 PM
It’s a sin that this happened to Adam. A true world class frontend engineer and a world class human. I remember being so excited when we first spoke about him joining Chrome and then talking VisBug. And he’s gone from strength to strength. What an epic own goal.
Vibe coding is the Polaroid camera of development.
March 28, 2025 at 1:58 PM
Vibe coding is the Polaroid camera of development.
Excited to launch the landscape and start to really curate the tools that devs should be aware of as we use AI to get better and building software!
Announcing the AI Native Dev Landscape: A place for developers to understand the AI tools that help them build software faster and better. Be the first to hear about new products and keep track of updates! ainativedev.co/yom
March 26, 2025 at 3:56 PM
Excited to launch the landscape and start to really curate the tools that devs should be aware of as we use AI to get better and building software!
I’m excited to get posting here about all things related to developing software with the new power of AI! #ainativedev
📢 The AI Native Dev website is officially LIVE! 🎉 Dive into the ultimate resource for AI Native Development tools, tutorials, and insights. Start exploring today: tessl.co/4bJAhoY #AINative #DevTools
AI Native Dev
The latest news and insights on AI powered dev tools and practices.
tessl.co
March 12, 2025 at 5:28 PM
I’m excited to get posting here about all things related to developing software with the new power of AI! #ainativedev
I giggle whenever I see this in prompts:
```
IMPORTANT: Use valid markdown only for all your responses and DO NOT use HTML tags except for artifacts!
ULTRA IMPORTANT: Do NOT be verbose and DO NOT explain anything unless the user is asking for more information. That is VERY important.
```
```
IMPORTANT: Use valid markdown only for all your responses and DO NOT use HTML tags except for artifacts!
ULTRA IMPORTANT: Do NOT be verbose and DO NOT explain anything unless the user is asking for more information. That is VERY important.
```
February 20, 2025 at 5:10 PM
I giggle whenever I see this in prompts:
```
IMPORTANT: Use valid markdown only for all your responses and DO NOT use HTML tags except for artifacts!
ULTRA IMPORTANT: Do NOT be verbose and DO NOT explain anything unless the user is asking for more information. That is VERY important.
```
```
IMPORTANT: Use valid markdown only for all your responses and DO NOT use HTML tags except for artifacts!
ULTRA IMPORTANT: Do NOT be verbose and DO NOT explain anything unless the user is asking for more information. That is VERY important.
```
Late binding of choices is a good thing and helps with choice fatigue.
Convention over configuration helps here, and LLMs being able to “fill in the gaps” takes it to a whole new level.
It favors getting things working and iterating from there in a tight loop.
Convention over configuration helps here, and LLMs being able to “fill in the gaps” takes it to a whole new level.
It favors getting things working and iterating from there in a tight loop.
February 19, 2025 at 3:20 PM
Late binding of choices is a good thing and helps with choice fatigue.
Convention over configuration helps here, and LLMs being able to “fill in the gaps” takes it to a whole new level.
It favors getting things working and iterating from there in a tight loop.
Convention over configuration helps here, and LLMs being able to “fill in the gaps” takes it to a whole new level.
It favors getting things working and iterating from there in a tight loop.
Voice is a great way to sculpt vs draw. You can be loose, go back and forth, and it isn’t about speaking the perfect thing which is what always held me back. Voice has become a real input for me these days. You?
February 13, 2025 at 11:01 PM
Voice is a great way to sculpt vs draw. You can be loose, go back and forth, and it isn’t about speaking the perfect thing which is what always held me back. Voice has become a real input for me these days. You?