Allen Pike
@allenpike.com
Building Forestwalk.ai, hosting Infer and It Shipped That Way, and writing about software and other tricky things. ⭐️
Vancouver • @apike elsewhere • allenpike.com
Vancouver • @apike elsewhere • allenpike.com
Good meetings are clear and short. Over the last couple weeks we’ve prototyped an agent that can join calls and build realtime notes – not a transcript, just clarity on key decisions.
A lot more to do, but having fun with this one 🌱 www.youtube.com/watch?v=Z2_7...
A lot more to do, but having fun with this one 🌱 www.youtube.com/watch?v=Z2_7...
Cedarloop on Zoom Demo – Nov 2025
Over the last two weeks at Forestwalk we’ve prototyped a realtime meeting notetaker agent. We think this could help teams get clarity faster, and ultimately have shorter and more useful meetings.
If…
www.youtube.com
November 10, 2025 at 7:40 PM
Good meetings are clear and short. Over the last couple weeks we’ve prototyped an agent that can join calls and build realtime notes – not a transcript, just clarity on key decisions.
A lot more to do, but having fun with this one 🌱 www.youtube.com/watch?v=Z2_7...
A lot more to do, but having fun with this one 🌱 www.youtube.com/watch?v=Z2_7...
Finally tried gpt-5-mini on some tasks, hoping at "minimal" reasoning it would be faster than claude-haiku-4.5 or gpt-4.1-mini.
Nope. Two other teams said 5-mini is so slow and unreliable that they can't use it either. Apparently "4 lightning bolts" means "takes 5-10s to process 200 tokens" 💫
Nope. Two other teams said 5-mini is so slow and unreliable that they can't use it either. Apparently "4 lightning bolts" means "takes 5-10s to process 200 tokens" 💫
November 6, 2025 at 11:05 PM
Finally tried gpt-5-mini on some tasks, hoping at "minimal" reasoning it would be faster than claude-haiku-4.5 or gpt-4.1-mini.
Nope. Two other teams said 5-mini is so slow and unreliable that they can't use it either. Apparently "4 lightning bolts" means "takes 5-10s to process 200 tokens" 💫
Nope. Two other teams said 5-mini is so slow and unreliable that they can't use it either. Apparently "4 lightning bolts" means "takes 5-10s to process 200 tokens" 💫
How to Not Get Acquired: An approach for minimizing distraction when trying to do something rather hard. allenpike.com/2025/how-not...
How to Not Get Acquired
Distraction management in intense times.
allenpike.com
November 1, 2025 at 6:36 AM
How to Not Get Acquired: An approach for minimizing distraction when trying to do something rather hard. allenpike.com/2025/how-not...
While the AWS team has resolved the severe us-east-1 outages, reading this post-mortem makes one thing clear: they are still suffering from a critical shortage of paragraph breaks
October 23, 2025 at 5:49 PM
While the AWS team has resolved the severe us-east-1 outages, reading this post-mortem makes one thing clear: they are still suffering from a critical shortage of paragraph breaks
“When we released Vision Pro, it provided glimpse of what spatial computing can be. Consistently, though, we’ve heard your concerns about weight and comfort. That’s why we’ve made the M5 Vision Pro 25% heavier – ensuring it is pressing on your nose, cheeks, and face with unprecedented heft”
October 16, 2025 at 10:04 PM
“When we released Vision Pro, it provided glimpse of what spatial computing can be. Consistently, though, we’ve heard your concerns about weight and comfort. That’s why we’ve made the M5 Vision Pro 25% heavier – ensuring it is pressing on your nose, cheeks, and face with unprecedented heft”
Building Something Big: On the pros and cons of the indie path. allenpike.com/2025/buildin...
Building Something Big
On the pros and cons of the indie path.
allenpike.com
September 1, 2025 at 6:28 AM
Building Something Big: On the pros and cons of the indie path. allenpike.com/2025/buildin...
Cursor's UI is nicer than using Claude Code in a terminal, but one helpful thing about Claude is that you can script hooks. For example, with an agent going on each screen, you can have Claude chime where it needs review or approval – panned left for the left screen, or right for the right. 🔊
August 12, 2025 at 9:10 PM
Cursor's UI is nicer than using Claude Code in a terminal, but one helpful thing about Claude is that you can script hooks. For example, with an agent going on each screen, you can have Claude chime where it needs review or approval – panned left for the left screen, or right for the right. 🔊
If you're getting weird behaviour from ChatGPT 5, check "What traits should ChatGPT have?" under Customize ChatGPT. I had this prompt there to help 4o be more critical, but they trained GPT-5 to be more critical by default, so the prompt pushed it into overcaffeinated paranoia.
August 7, 2025 at 11:19 PM
If you're getting weird behaviour from ChatGPT 5, check "What traits should ChatGPT have?" under Customize ChatGPT. I had this prompt there to help 4o be more critical, but they trained GPT-5 to be more critical by default, so the prompt pushed it into overcaffeinated paranoia.
Spending Too Much Money on a Coding Agent: Some perks and pitfalls of building with large thinking models. allenpike.com/2025/coding-...
Spending Too Much Money on a Coding Agent
On making use of large thinking models.
allenpike.com
July 1, 2025 at 5:18 AM
Spending Too Much Money on a Coding Agent: Some perks and pitfalls of building with large thinking models. allenpike.com/2025/coding-...
I almost deleted this notification without thinking, but stopped to read it in a different light. When you have a lot left to do, it's easy to miss the little moments that represent that you're making progress.
So here's to that. 🍻
So here's to that. 🍻
June 25, 2025 at 5:12 PM
I almost deleted this notification without thinking, but stopped to read it in a different light. When you have a lot left to do, it's easy to miss the little moments that represent that you're making progress.
So here's to that. 🍻
So here's to that. 🍻
Supposedly Meta was withholding WhatsApp and Instagram for iPad to get some App Store policy change. They've just announced both, the week before WWDC, trumpeting Magic Keyboard and Apple Pencil support – implying that they got what they wanted.
I wonder if we'll be able to tell what they got? 🤔
I wonder if we'll be able to tell what they got? 🤔
June 3, 2025 at 11:09 PM
Supposedly Meta was withholding WhatsApp and Instagram for iPad to get some App Store policy change. They've just announced both, the week before WWDC, trumpeting Magic Keyboard and Apple Pencil support – implying that they got what they wanted.
I wonder if we'll be able to tell what they got? 🤔
I wonder if we'll be able to tell what they got? 🤔
Figma Slides is a Beautiful Disaster: The best and the worst of an interesting new tool. allenpike.com/2025/figma-s...
Figma Slides is a Beautiful Disaster
Some highlights and lowlights.
allenpike.com
June 1, 2025 at 5:01 AM
Figma Slides is a Beautiful Disaster: The best and the worst of an interesting new tool. allenpike.com/2025/figma-s...
Libraries often have private, internal API surfaces that must not be depended on. It is important to name these dangerous APIs in an alarming way. This ensures that any consumers of your library will be embarrassed when they inevitably use them anyway
May 22, 2025 at 3:03 PM
Libraries often have private, internal API surfaces that must not be depended on. It is important to name these dangerous APIs in an alarming way. This ensures that any consumers of your library will be embarrassed when they inevitably use them anyway
In two weeks OpenAI has added Instacart's CEO, the Windsurf staff, and Sir Jony Ive himself to their team.
If they can continue this pace, OpenAI may eventually amass the talent necessary to overcome the ultimate product challenge: designing a reasonable model selection UI
If they can continue this pace, OpenAI may eventually amass the talent necessary to overcome the ultimate product challenge: designing a reasonable model selection UI
May 21, 2025 at 7:27 PM
In two weeks OpenAI has added Instacart's CEO, the Windsurf staff, and Sir Jony Ive himself to their team.
If they can continue this pace, OpenAI may eventually amass the talent necessary to overcome the ultimate product challenge: designing a reasonable model selection UI
If they can continue this pace, OpenAI may eventually amass the talent necessary to overcome the ultimate product challenge: designing a reasonable model selection UI
Reposted by Allen Pike
Super VanJS is here.
On May 15th, we celebrate JavaScript in style.
Get ready for amazing talks from top speakers:
- Allen Pike: JavaScript Frameworks SOTU – Fatigue Strikes Back
- Shawn McKay: Untangling a large codebase
- @jasnell.me : What Node.js Compatibility Really Means
On May 15th, we celebrate JavaScript in style.
Get ready for amazing talks from top speakers:
- Allen Pike: JavaScript Frameworks SOTU – Fatigue Strikes Back
- Shawn McKay: Untangling a large codebase
- @jasnell.me : What Node.js Compatibility Really Means
May 8, 2025 at 11:02 AM
Super VanJS is here.
On May 15th, we celebrate JavaScript in style.
Get ready for amazing talks from top speakers:
- Allen Pike: JavaScript Frameworks SOTU – Fatigue Strikes Back
- Shawn McKay: Untangling a large codebase
- @jasnell.me : What Node.js Compatibility Really Means
On May 15th, we celebrate JavaScript in style.
Get ready for amazing talks from top speakers:
- Allen Pike: JavaScript Frameworks SOTU – Fatigue Strikes Back
- Shawn McKay: Untangling a large codebase
- @jasnell.me : What Node.js Compatibility Really Means
Reposted by Allen Pike
Every developer has a story. What's yours?
Whether you’re a seasoned speaker or stepping on stage for the first time, our CFP is open.
Speakers get a conf ticket, travel & hotel covered, support, and a few fun surprises. Plus, you'll be speaking to one of the most welcoming audiences around.
Whether you’re a seasoned speaker or stepping on stage for the first time, our CFP is open.
Speakers get a conf ticket, travel & hotel covered, support, and a few fun surprises. Plus, you'll be speaking to one of the most welcoming audiences around.
May 5, 2025 at 8:46 PM
Every developer has a story. What's yours?
Whether you’re a seasoned speaker or stepping on stage for the first time, our CFP is open.
Speakers get a conf ticket, travel & hotel covered, support, and a few fun surprises. Plus, you'll be speaking to one of the most welcoming audiences around.
Whether you’re a seasoned speaker or stepping on stage for the first time, our CFP is open.
Speakers get a conf ticket, travel & hotel covered, support, and a few fun surprises. Plus, you'll be speaking to one of the most welcoming audiences around.
The video from our last Infer meetup is now up. It features David Hariri and Kosta Djukic from Ada Support, sharing lessons learned serving 4 billion interactions (and counting) with AI. www.youtube.com/watch?v=JSmQ...
Lessons Learned Scaling LLMs @ Ada – David Hariri & Kosta Djukic (Infer, Mar ’25)
YouTube video by Infer Vancouver
www.youtube.com
May 7, 2025 at 9:46 PM
The video from our last Infer meetup is now up. It features David Hariri and Kosta Djukic from Ada Support, sharing lessons learned serving 4 billion interactions (and counting) with AI. www.youtube.com/watch?v=JSmQ...
I was invited to share what I've been learning about UX patterns for non-chat AI products at the Vancouver AI Meetup last week, and the video is already up ⭐️ www.youtube.com/watch?v=mRqB...
May 5, 2025 at 3:57 PM
I was invited to share what I've been learning about UX patterns for non-chat AI products at the Vancouver AI Meetup last week, and the video is already up ⭐️ www.youtube.com/watch?v=mRqB...
Post-Chat UI: Delightful and humane patterns for the next generation of apps. allenpike.com/2025/post-ch...
Post-Chat UI
How LLMs are making traditional apps feel broken.
allenpike.com
May 1, 2025 at 4:17 PM
Post-Chat UI: Delightful and humane patterns for the next generation of apps. allenpike.com/2025/post-ch...
A Score for Snacks: The trouble with snacks, the Nutri-Score, and a calculator for it.
A Score for Snacks
The Nutri-Score, and a calculator for it.
allenpike.com
March 31, 2025 at 11:44 PM
A Score for Snacks: The trouble with snacks, the Nutri-Score, and a calculator for it.
The Periodic Table of Elements, according to GPT-4o's new, smarter image generation
March 25, 2025 at 7:53 PM
The Periodic Table of Elements, according to GPT-4o's new, smarter image generation
JavaScript Fatigue Strikes Back: Why we still have so many JS frameworks, and why maybe – maybe – we have enough now?
JavaScript Fatigue Strikes Back
The new frameworks will continue until morale improves.
allenpike.com
March 1, 2025 at 7:29 AM
JavaScript Fatigue Strikes Back: Why we still have so many JS frameworks, and why maybe – maybe – we have enough now?
Initial impressions of GPT-4.5 is that it's noticeably more “personable” – easier to prompt into behaving more idiosyncratically and less like a wikipedia page.
I've put a little 4.5-powered "product research agent" in the corner of forestwalk.ai if you're curious how this can feel in practice.
I've put a little 4.5-powered "product research agent" in the corner of forestwalk.ai if you're curious how this can feel in practice.
Forestwalk Labs
Tools for software teams building on LLMs.
forestwalk.ai
February 27, 2025 at 10:45 PM
Initial impressions of GPT-4.5 is that it's noticeably more “personable” – easier to prompt into behaving more idiosyncratically and less like a wikipedia page.
I've put a little 4.5-powered "product research agent" in the corner of forestwalk.ai if you're curious how this can feel in practice.
I've put a little 4.5-powered "product research agent" in the corner of forestwalk.ai if you're curious how this can feel in practice.