It’s 2026, so another basic technique that every team should add to their testing strategy (in addition to proven techniques like fuzzing) is agentic user simulation. Set up an AI agent with access to the product, and…
Yeah I think this is a good approach. I’m pretty AI-optimistic when it comes to making code changes. But reading AI generated descriptions (including pull requests) is absolutely the worst. That content really needs to…
Slowing down development is the wrong goal. I see a desire for slowness come up a lot with developers. If you pursue that goal all the way to its logical conclusion then eventually you would stop all coding completely.…
old and inaccurate knowledge.. - Skills do take up space in the context. The name and description of every skill goes into the system prompt. You can't add unlimited skills without context pressure. - MCP context spam…
Good question but people are doing it anyway. It's a fact that right now tons of people are buying Mac Minis specifically for this use case, to treat them as their personal data center for agents. The concept of "power…
That's a lot of assumptions. I think there are also people buying new hardware specifically for this purpose, and their motivation to do it is thinking it will be cheaper in the long run. Privacy is not necessarily the…
The time difference does matter though. There were some recent worm attacks in NPM that spread very quickly because they used post-install. I don’t remember how long it took NPM to block the packages but it was probably…
There’s a difference between: 1) the minimum number of employees it takes to maintain the core product Vs 2) All the employees that it makes sense to hire for revenue and market expansion. Internet comments usually…
Offshoring has been a common practice for decades, it works great for some functions and not great for others. Why would it suddenly have a massive uptick in 2027?
If you look at IOS app store submissions then there is a pretty obvious increase that lines up with recent AI tooling (especially the release of Claude Code):…
In a world of AI coding I think rule 5 is still as important than ever. I don’t validate everything Claude does but I do put attention on data structure design since it’s so important.
Hiring a human is gambling too.
Lol anyway, the point is that even in a scenario where all the major models disappeared tomorrow (including OpenAI, Anthropic, etc), we would still keep using the existing open source models (GLM, Deepseek, Qwen) for a…
> it's the running costs of these major AI services that are also astronomical There's wildly different reports about whether the cost of just inference (not the training) is expensive or not... Sam Altman has said…
Great analogy. I've never worked at a company as large as Google but in my experience things can be a little more optimistic than the post. When earn enough trust with your leadership, such as at the staff/architect…
It was just a few months ago that the MCP spec added a concept called "prompts" which are really similar to skills. And of course Claude Code has custom slash commands which are also very similar. Getting a lot of…
to some degree this is a "market correction" on the inherent value of these papers. There's way too many low-value papers that are being published purely for career advancement and CV padding reasons. Hard to get peer…
> AI as a product isn’t viable Yeah I don't know about that, the model providers like OpenAI, Anthropic, etc, literally sell intelligence as a product. And their business model is looking a lot more stable in the long…
Simplest version of Kubernetes is zero Kubernetes. You can instead run your service using a process manager like PM2 or similar. I think even using Docker is overkill for a lot of small teams.
That's a good concept but I don't think Markdown is expressive enough for all the layouts & formatting that people typically want in PDFs. More likely that the source format would be something like HTML or SVG or .docx.
Working on dev tools for MCP servers. As a building block I recently published a library to help write tests for MCPs - https://facetlayer.github.io/expect-mcp/
It’s 2026, so another basic technique that every team should add to their testing strategy (in addition to proven techniques like fuzzing) is agentic user simulation. Set up an AI agent with access to the product, and…
Yeah I think this is a good approach. I’m pretty AI-optimistic when it comes to making code changes. But reading AI generated descriptions (including pull requests) is absolutely the worst. That content really needs to…
Slowing down development is the wrong goal. I see a desire for slowness come up a lot with developers. If you pursue that goal all the way to its logical conclusion then eventually you would stop all coding completely.…
old and inaccurate knowledge.. - Skills do take up space in the context. The name and description of every skill goes into the system prompt. You can't add unlimited skills without context pressure. - MCP context spam…
Good question but people are doing it anyway. It's a fact that right now tons of people are buying Mac Minis specifically for this use case, to treat them as their personal data center for agents. The concept of "power…
That's a lot of assumptions. I think there are also people buying new hardware specifically for this purpose, and their motivation to do it is thinking it will be cheaper in the long run. Privacy is not necessarily the…
The time difference does matter though. There were some recent worm attacks in NPM that spread very quickly because they used post-install. I don’t remember how long it took NPM to block the packages but it was probably…
There’s a difference between: 1) the minimum number of employees it takes to maintain the core product Vs 2) All the employees that it makes sense to hire for revenue and market expansion. Internet comments usually…
Offshoring has been a common practice for decades, it works great for some functions and not great for others. Why would it suddenly have a massive uptick in 2027?
If you look at IOS app store submissions then there is a pretty obvious increase that lines up with recent AI tooling (especially the release of Claude Code):…
In a world of AI coding I think rule 5 is still as important than ever. I don’t validate everything Claude does but I do put attention on data structure design since it’s so important.
Hiring a human is gambling too.
Lol anyway, the point is that even in a scenario where all the major models disappeared tomorrow (including OpenAI, Anthropic, etc), we would still keep using the existing open source models (GLM, Deepseek, Qwen) for a…
> it's the running costs of these major AI services that are also astronomical There's wildly different reports about whether the cost of just inference (not the training) is expensive or not... Sam Altman has said…
Great analogy. I've never worked at a company as large as Google but in my experience things can be a little more optimistic than the post. When earn enough trust with your leadership, such as at the staff/architect…
It was just a few months ago that the MCP spec added a concept called "prompts" which are really similar to skills. And of course Claude Code has custom slash commands which are also very similar. Getting a lot of…
to some degree this is a "market correction" on the inherent value of these papers. There's way too many low-value papers that are being published purely for career advancement and CV padding reasons. Hard to get peer…
> AI as a product isn’t viable Yeah I don't know about that, the model providers like OpenAI, Anthropic, etc, literally sell intelligence as a product. And their business model is looking a lot more stable in the long…
Simplest version of Kubernetes is zero Kubernetes. You can instead run your service using a process manager like PM2 or similar. I think even using Docker is overkill for a lot of small teams.
That's a good concept but I don't think Markdown is expressive enough for all the layouts & formatting that people typically want in PDFs. More likely that the source format would be something like HTML or SVG or .docx.
Working on dev tools for MCP servers. As a building block I recently published a library to help write tests for MCPs - https://facetlayer.github.io/expect-mcp/