Aymeric C.
@engaym.bsky.social
Engineering Swiss army knife • Engineering Manager @ Mercari in 🇯🇵
Reposted by Aymeric C.
Ben Thompson argues that while AI is obviously in a bubble, it will create long term benefits in the form of investments in chip fabs in the U.S. and power plants.
This is similar to how we got dark fiber and train tracks as infrastructure out of the internet and railway bubbles.
This is similar to how we got dark fiber and train tracks as infrastructure out of the internet and railway bubbles.
The Benefits of Bubbles
We are in an AI Bubble: the big question is if this bubble will be worth it for the physical infrastructure and coordinated innovation that result?
stratechery.com
November 7, 2025 at 4:13 PM
Ben Thompson argues that while AI is obviously in a bubble, it will create long term benefits in the form of investments in chip fabs in the U.S. and power plants.
This is similar to how we got dark fiber and train tracks as infrastructure out of the internet and railway bubbles.
This is similar to how we got dark fiber and train tracks as infrastructure out of the internet and railway bubbles.
Quick intro to Claude Skills
Simplicity is the point.
The most significant limitation of MCP is token usage
Almost everything an MCP can do, can also be handled by a CLI tool instead. LLMs know how to call cli-tool --help, which means you don’t have to spend many tokens describing how to use them
Simplicity is the point.
The most significant limitation of MCP is token usage
Almost everything an MCP can do, can also be handled by a CLI tool instead. LLMs know how to call cli-tool --help, which means you don’t have to spend many tokens describing how to use them
Claude Skills are awesome, maybe a bigger deal than MCP
simonwillison.net/2025/Oct/16/...
simonwillison.net/2025/Oct/16/...
Claude Skills are awesome, maybe a bigger deal than MCP
Anthropic this morning introduced Claude Skills, a new pattern for making new abilities available to their models: Claude can now use Skills to improve how it performs specific tasks. Skills …
simonwillison.net
October 26, 2025 at 2:02 PM
Quick intro to Claude Skills
Simplicity is the point.
The most significant limitation of MCP is token usage
Almost everything an MCP can do, can also be handled by a CLI tool instead. LLMs know how to call cli-tool --help, which means you don’t have to spend many tokens describing how to use them
Simplicity is the point.
The most significant limitation of MCP is token usage
Almost everything an MCP can do, can also be handled by a CLI tool instead. LLMs know how to call cli-tool --help, which means you don’t have to spend many tokens describing how to use them
What happens to a driving Waymo when AWS us-east-1 goes down? 😅
Is everything processed locally?
It’s an Alphabet company, so if something is remote, I’d expect it to be on GCP or Google internal platforms, but with external dependencies, isn’t every product 6 degrees of separation from us-east-1?
Is everything processed locally?
It’s an Alphabet company, so if something is remote, I’d expect it to be on GCP or Google internal platforms, but with external dependencies, isn’t every product 6 degrees of separation from us-east-1?
October 20, 2025 at 2:37 PM
What happens to a driving Waymo when AWS us-east-1 goes down? 😅
Is everything processed locally?
It’s an Alphabet company, so if something is remote, I’d expect it to be on GCP or Google internal platforms, but with external dependencies, isn’t every product 6 degrees of separation from us-east-1?
Is everything processed locally?
It’s an Alphabet company, so if something is remote, I’d expect it to be on GCP or Google internal platforms, but with external dependencies, isn’t every product 6 degrees of separation from us-east-1?
Reposted by Aymeric C.
Okay, for the folks who asked: here's the majority AI view, writing up the reasonable, thoughtful view on AI that the vast majority of people in tech hold, that gets overshadowed by the bluster and hype of the tycoons trying to shill their nonsense. anildash.com/2025/10/17/t... Please share!
The Majority AI View - Anil Dash
A blog about making culture. Since 1999.
anildash.com
October 17, 2025 at 7:29 PM
Okay, for the folks who asked: here's the majority AI view, writing up the reasonable, thoughtful view on AI that the vast majority of people in tech hold, that gets overshadowed by the bluster and hype of the tycoons trying to shill their nonsense. anildash.com/2025/10/17/t... Please share!
This is the first article I read about spec-driven development and this is a good introduction.
I thought spec meant PRD, but it’s more of a detailed technical design.
As a profession, we were not good at documentation before AI, so this will not suit many orgs.
And it seems overkill in most cases.
I thought spec meant PRD, but it’s more of a detailed technical design.
As a profession, we were not good at documentation before AI, so this will not suit many orgs.
And it seems overkill in most cases.
I tried to make sense of "spec-driven development" by looking at 3 tools: Amazon's Kiro, GitHub's spec-kit, and the Tessl Framework
martinfowler.com/articles/exp...
martinfowler.com/articles/exp...
Understanding Spec-Driven-Development: Kiro, spec-kit, and Tessl
Notes from my Thoughtworks colleagues on AI-assisted software delivery
martinfowler.com
October 16, 2025 at 11:01 PM
This is the first article I read about spec-driven development and this is a good introduction.
I thought spec meant PRD, but it’s more of a detailed technical design.
As a profession, we were not good at documentation before AI, so this will not suit many orgs.
And it seems overkill in most cases.
I thought spec meant PRD, but it’s more of a detailed technical design.
As a profession, we were not good at documentation before AI, so this will not suit many orgs.
And it seems overkill in most cases.
I wrote an article on how we translate user-generated content at scale at Mercari.
It summarizes two years of work with various models, LLMs but not only, and how cost evolved, reducing it 100x over the period.
I also go over non-AI features and user experience.
It summarizes two years of work with various models, LLMs but not only, and how cost evolved, reducing it 100x over the period.
I also go over non-AI features and user experience.
The Journey of User-Generated Content Translation | Mercari Engineering
This is @aymeric from Cross Border Engineering.This article is part of the blog series Behind the Scenes of Developing M
engineering.mercari.com
October 12, 2025 at 12:36 AM
I wrote an article on how we translate user-generated content at scale at Mercari.
It summarizes two years of work with various models, LLMs but not only, and how cost evolved, reducing it 100x over the period.
I also go over non-AI features and user experience.
It summarizes two years of work with various models, LLMs but not only, and how cost evolved, reducing it 100x over the period.
I also go over non-AI features and user experience.
Our engineering team took on the massive challenge of rebuilding our marketplace from scratch to make it scale globally 🌏, and we just launched it. 🚀
Check out the first article in our blog series to learn how we did it!
Check out the first article in our blog series to learn how we did it!
Behind the Scenes of Developing Mercari’s First Global App, “Mercari Global App” | Mercari Engineering
Hello. I’m @deeeeet from Cross Border (XB) Engineering.On September 30, 2025, we announced a new strategy for our
engineering.mercari.com
October 9, 2025 at 6:30 AM
Our engineering team took on the massive challenge of rebuilding our marketplace from scratch to make it scale globally 🌏, and we just launched it. 🚀
Check out the first article in our blog series to learn how we did it!
Check out the first article in our blog series to learn how we did it!
The best description of Product vs Platform engineering 😂
Like the tail of an enthusiastic puppy:
The product work might go a thousand directions in a minute. They're at the end of the puppy's tail. Infrastructure is the part of the tail anchored to its butt, not changing direction nearly as fast
Like the tail of an enthusiastic puppy:
The product work might go a thousand directions in a minute. They're at the end of the puppy's tail. Infrastructure is the part of the tail anchored to its butt, not changing direction nearly as fast
Google+ was wildly successful, just not as a product.
I worked on infrastructure teams at Google for a long time. One of the eras I lived through was the rise and fall of Google+, their foray into… |...
Google+ was wildly successful, just not as a product.
I worked on infrastructure teams at Google for a long time. One of the eras I lived through was the rise and fall of Google+, their foray into so...
www.linkedin.com
September 30, 2025 at 5:11 AM
The best description of Product vs Platform engineering 😂
Like the tail of an enthusiastic puppy:
The product work might go a thousand directions in a minute. They're at the end of the puppy's tail. Infrastructure is the part of the tail anchored to its butt, not changing direction nearly as fast
Like the tail of an enthusiastic puppy:
The product work might go a thousand directions in a minute. They're at the end of the puppy's tail. Infrastructure is the part of the tail anchored to its butt, not changing direction nearly as fast
Great article explaining what atproto is about in non-technical terms.
Excerpts:
We are at a similar juncture with social apps as we have been with open source thirty five years ago […] I like to call it “open social”
What open source did for code, open social does for data.
Excerpts:
We are at a similar juncture with social apps as we have been with open source thirty five years ago […] I like to call it “open social”
What open source did for code, open social does for data.
i wrote about atproto and why it matters
Open Social — overreacted
The protocol is the API.
overreacted.io
September 28, 2025 at 3:53 PM
Great article explaining what atproto is about in non-technical terms.
Excerpts:
We are at a similar juncture with social apps as we have been with open source thirty five years ago […] I like to call it “open social”
What open source did for code, open social does for data.
Excerpts:
We are at a similar juncture with social apps as we have been with open source thirty five years ago […] I like to call it “open social”
What open source did for code, open social does for data.
A good thread on retaining top engineers, how it sometimes means encouraging them to take on roles outside your org
I’d rather keep top talent in the company by sharing opportunities outside my org, rather than keeping them locked and they leave later out of boredom or lack of growth opportunities
I’d rather keep top talent in the company by sharing opportunities outside my org, rather than keeping them locked and they leave later out of boredom or lack of growth opportunities
It can sometimes?
And over-qualified doesn't always mean paid more.
My approach is different than many hiring managers. I'm not as afraid of someone leaving in a short time for a better opportunity. I even introduce my team to other opportunities!
It's my job to earn their retention.
And over-qualified doesn't always mean paid more.
My approach is different than many hiring managers. I'm not as afraid of someone leaving in a short time for a better opportunity. I even introduce my team to other opportunities!
It's my job to earn their retention.
does being overqualified for a job mean something other than “we want to pay someone less for this role”?
September 14, 2025 at 2:43 AM
A good thread on retaining top engineers, how it sometimes means encouraging them to take on roles outside your org
I’d rather keep top talent in the company by sharing opportunities outside my org, rather than keeping them locked and they leave later out of boredom or lack of growth opportunities
I’d rather keep top talent in the company by sharing opportunities outside my org, rather than keeping them locked and they leave later out of boredom or lack of growth opportunities
Maybe social media needs circuit breakers like when the stock exchange crashes.
If the mod team can’t remove hateful content fast enough, block the entire system: no posting, maybe even no viewing.
Stop the snowball effect and let the mod team catch up.
Put a SLO on the number of unack’ed reports.
If the mod team can’t remove hateful content fast enough, block the entire system: no posting, maybe even no viewing.
Stop the snowball effect and let the mod team catch up.
Put a SLO on the number of unack’ed reports.
When there’s a lot of activity on the site, our dedicated mod team works around the clock to keep you safe and uphold our community standards. If you think there was a mistake, you can appeal by emailing [email protected] and they will get to it as soon as they can.
September 14, 2025 at 2:15 AM
Maybe social media needs circuit breakers like when the stock exchange crashes.
If the mod team can’t remove hateful content fast enough, block the entire system: no posting, maybe even no viewing.
Stop the snowball effect and let the mod team catch up.
Put a SLO on the number of unack’ed reports.
If the mod team can’t remove hateful content fast enough, block the entire system: no posting, maybe even no viewing.
Stop the snowball effect and let the mod team catch up.
Put a SLO on the number of unack’ed reports.
Reposted by Aymeric C.
I've been reading this on the Month of AI bugs from @wuzzi23.bsky.social and I am losing my fucking mind. The series is excellent, and Johann does great work, but SWEET FUCK people, you cannot be serious here.
This is absolute clownshoes territory
embracethered.com/blog/posts/2...
This is absolute clownshoes territory
embracethered.com/blog/posts/2...
Wrap Up: The Month of AI Bugs · Embrace The Red
Wrap Up: The Month of AI Bugs - Full List of Postings
embracethered.com
September 3, 2025 at 5:21 AM
I've been reading this on the Month of AI bugs from @wuzzi23.bsky.social and I am losing my fucking mind. The series is excellent, and Johann does great work, but SWEET FUCK people, you cannot be serious here.
This is absolute clownshoes territory
embracethered.com/blog/posts/2...
This is absolute clownshoes territory
embracethered.com/blog/posts/2...
Nice real world application of AI agents and lessons learned, full of interesting advices.
The analogy to Map Reduce is clever.
Keep it simple with two layers and no state in the sub-agents.
Caching is smart.
It attempts to make non-deterministic LLMs into agents as deterministic as possible.
The analogy to Map Reduce is clever.
Keep it simple with two layers and no state in the sub-agents.
Caching is smart.
It attempts to make non-deterministic LLMs into agents as deterministic as possible.
Best Practices for Building Agentic AI Systems: What Actually Works in Production - UserJot
Real patterns for building AI agent systems that don't fall apart. Two-tier architectures, stateless design, orchestration strategies, and what we learned building UserJot's agent infrastructure.
userjot.com
August 25, 2025 at 2:45 PM
Nice real world application of AI agents and lessons learned, full of interesting advices.
The analogy to Map Reduce is clever.
Keep it simple with two layers and no state in the sub-agents.
Caching is smart.
It attempts to make non-deterministic LLMs into agents as deterministic as possible.
The analogy to Map Reduce is clever.
Keep it simple with two layers and no state in the sub-agents.
Caching is smart.
It attempts to make non-deterministic LLMs into agents as deterministic as possible.
I love how one can share a bug on Bluesky and the main maintainer not only answers but also promises to fix it.
August 18, 2025 at 11:27 AM
I love how one can share a bug on Bluesky and the main maintainer not only answers but also promises to fix it.
Great new feature in VS Code, checkpoints in chat sessions with Copilot.
We finally can chat with the tool without having to commit between every request. If the next prompts mess up, just revert to the previous stable state.
We finally can chat with the tool without having to commit between every request. If the next prompts mess up, just revert to the previous stable state.
July 2025 (version 1.103)
Learn what is new in the Visual Studio Code July 2025 Release (1.103)
code.visualstudio.com
August 17, 2025 at 9:02 AM
Great new feature in VS Code, checkpoints in chat sessions with Copilot.
We finally can chat with the tool without having to commit between every request. If the next prompts mess up, just revert to the previous stable state.
We finally can chat with the tool without having to commit between every request. If the next prompts mess up, just revert to the previous stable state.
Great summary by @simonwillison.net of @wuzzi23.bsky.social ‘s findings on AI tools vulnerabilities.
In short, all AI tools are vulnerable if one attaches external files and links to their prompts, leading to secrets leaks and remote code execution.
Johann publishes daily until the end of the month.
In short, all AI tools are vulnerable if one attaches external files and links to their prompts, leading to secrets leaks and remote code execution.
Johann publishes daily until the end of the month.
The Summer of Johann: prompt injections as far as the eye can see
Independent AI researcher Johann Rehberger (previously) has had an absurdly busy August. Under the heading The Month of AI Bugs he has been publishing one report per day across an …
simonwillison.net
August 17, 2025 at 5:02 AM
Great summary by @simonwillison.net of @wuzzi23.bsky.social ‘s findings on AI tools vulnerabilities.
In short, all AI tools are vulnerable if one attaches external files and links to their prompts, leading to secrets leaks and remote code execution.
Johann publishes daily until the end of the month.
In short, all AI tools are vulnerable if one attaches external files and links to their prompts, leading to secrets leaks and remote code execution.
Johann publishes daily until the end of the month.
Reposted by Aymeric C.
LinkedIn is broken. All your data is trapped behind a walled garden, job applications never seem to go anywhere, and the whole site increasingly seems to be an ad to try to upsell you LinkedIn Premium.
We're here to help. For Pros on Proto to connect Pro to Pro!
We're here to help. For Pros on Proto to connect Pro to Pro!
July 4, 2025 at 6:19 PM
LinkedIn is broken. All your data is trapped behind a walled garden, job applications never seem to go anywhere, and the whole site increasingly seems to be an ad to try to upsell you LinkedIn Premium.
We're here to help. For Pros on Proto to connect Pro to Pro!
We're here to help. For Pros on Proto to connect Pro to Pro!
I love how @bsky.app gets built in public, to the point that core contributors use the app to post bugs and tag colleagues 😄
this flicker when the video crosses some threshold is annoying. why even unload it in this case? there are no competing videos in the viewport, might as well let it run until it actually goes offscreen. or at least fix the flash somehow
August 12, 2025 at 12:17 PM
I love how @bsky.app gets built in public, to the point that core contributors use the app to post bugs and tag colleagues 😄
The first job of a leader is to make the business succeed.
This is a common point of these three articles from 2011, 2024 and 2025
- a16z: Peacetime CEO / Wartime CEO
- Charity Majors: Pragamatism, neutrality and leadership
- Lara Hogan: Balancing direction and empowerment
This is a common point of these three articles from 2011, 2024 and 2025
- a16z: Peacetime CEO / Wartime CEO
- Charity Majors: Pragamatism, neutrality and leadership
- Lara Hogan: Balancing direction and empowerment
August 11, 2025 at 4:39 AM
The first job of a leader is to make the business succeed.
This is a common point of these three articles from 2011, 2024 and 2025
- a16z: Peacetime CEO / Wartime CEO
- Charity Majors: Pragamatism, neutrality and leadership
- Lara Hogan: Balancing direction and empowerment
This is a common point of these three articles from 2011, 2024 and 2025
- a16z: Peacetime CEO / Wartime CEO
- Charity Majors: Pragamatism, neutrality and leadership
- Lara Hogan: Balancing direction and empowerment
Reposted by Aymeric C.
I laughed so hard I thought I was going to cough up an organ. Every line is gold.
In the Future All Food Will Be Cooked in a Microwave, and if You Can’t Deal With That Then You Need to Get Out of the Kitchen
As a restaurant owner – I’m astounded at the rate of progress since microwaves were released a few short years ago. Today’s microwave can cook a frozen burrito. Tomorrow’s m…
www.colincornaby.me
August 4, 2025 at 11:06 PM
I laughed so hard I thought I was going to cough up an organ. Every line is gold.
On the impact of AI generated code.
From the article: The code that we rely on for bank transactions, package deliveries, medical results, satellite launches, airline flight paths, self-driving cars, mortgage payments, and nuclear power plants. This is durable code, and it’s going to stay that way.
From the article: The code that we rely on for bank transactions, package deliveries, medical results, satellite launches, airline flight paths, self-driving cars, mortgage payments, and nuclear power plants. This is durable code, and it’s going to stay that way.
Definitely not the first blog post inspired by a @monkchips.com comment, and won't be the last.
Monkchips is the sand in my oyster that makes beautiful pearls. 🦪😆💕
(Still mean to circle back to the question of what it means to have good technical taste...)
www.honeycomb.io/blog/disposa...
Monkchips is the sand in my oyster that makes beautiful pearls. 🦪😆💕
(Still mean to circle back to the question of what it means to have good technical taste...)
www.honeycomb.io/blog/disposa...
August 4, 2025 at 11:46 PM
On the impact of AI generated code.
From the article: The code that we rely on for bank transactions, package deliveries, medical results, satellite launches, airline flight paths, self-driving cars, mortgage payments, and nuclear power plants. This is durable code, and it’s going to stay that way.
From the article: The code that we rely on for bank transactions, package deliveries, medical results, satellite launches, airline flight paths, self-driving cars, mortgage payments, and nuclear power plants. This is durable code, and it’s going to stay that way.
💯
It’s always a trade-off.
The Career Tug-of-War: To do meaningful work with people you respect and admire. To lead with integrity. Part of you wants to climb.
It’s always a trade-off.
The Career Tug-of-War: To do meaningful work with people you respect and admire. To lead with integrity. Part of you wants to climb.
A Cautionary Tale For Stupid Idiots Who Think They Can Lead With Integrity
It's a terrible career move, but hey—at least you can sleep at night.
jamesjboyer.substack.com
August 2, 2025 at 8:02 AM
💯
It’s always a trade-off.
The Career Tug-of-War: To do meaningful work with people you respect and admire. To lead with integrity. Part of you wants to climb.
It’s always a trade-off.
The Career Tug-of-War: To do meaningful work with people you respect and admire. To lead with integrity. Part of you wants to climb.
Great reading that provides a clear structure.
Amongst them, I believe Avoid “us vs. them” language is pretty important to highlight.
The negativity can really make things worse.
Amongst them, I believe Avoid “us vs. them” language is pretty important to highlight.
The negativity can really make things worse.
How to communicate mandates (even if you disagree with them)
You may not agree with a mandate, but that shouldn't affect the way you communicate it to your team.
leaddev.com
August 2, 2025 at 7:19 AM
Great reading that provides a clear structure.
Amongst them, I believe Avoid “us vs. them” language is pretty important to highlight.
The negativity can really make things worse.
Amongst them, I believe Avoid “us vs. them” language is pretty important to highlight.
The negativity can really make things worse.
It’s awesome, we do that at Mercari and there are ~2000 employees.
It’s low noise channels, great to get context from areas of the company I don’t work with regularly, or catch news that I missed in the 100s of important but noisy channels.
And it’s great to get to know your colleagues personally.
It’s low noise channels, great to get context from areas of the company I don’t work with regularly, or catch news that I missed in the 100s of important but noisy channels.
And it’s great to get to know your colleagues personally.
August 2, 2025 at 6:21 AM
It’s awesome, we do that at Mercari and there are ~2000 employees.
It’s low noise channels, great to get context from areas of the company I don’t work with regularly, or catch news that I missed in the 100s of important but noisy channels.
And it’s great to get to know your colleagues personally.
It’s low noise channels, great to get context from areas of the company I don’t work with regularly, or catch news that I missed in the 100s of important but noisy channels.
And it’s great to get to know your colleagues personally.
I love documentation. I’ve constantly contributed a lot wherever I was.
It’s been a struggle trying to convince many of its usefulness until recently.
Humans could handle ambiguity. AI is not as tolerant.
Looks lime AI has convinced many that it is useful after all 😄
It’s been a struggle trying to convince many of its usefulness until recently.
Humans could handle ambiguity. AI is not as tolerant.
Looks lime AI has convinced many that it is useful after all 😄
August 1, 2025 at 2:20 PM
I love documentation. I’ve constantly contributed a lot wherever I was.
It’s been a struggle trying to convince many of its usefulness until recently.
Humans could handle ambiguity. AI is not as tolerant.
Looks lime AI has convinced many that it is useful after all 😄
It’s been a struggle trying to convince many of its usefulness until recently.
Humans could handle ambiguity. AI is not as tolerant.
Looks lime AI has convinced many that it is useful after all 😄