Diarmid Mackenzie
@dhmackenzie.bsky.social
Software, WebXR, Home Education, Self-determination Theory & Nonviolent Communication.
https://diarmid.online
Currently building: https://simpledraw.app
https://diarmid.online
Currently building: https://simpledraw.app
Something I've been working on over the last couple of months.
Driven by the frustration that I couldn't find a decent, simple, free online drawing tool to help with our building project.
Given time, I think it has the potential to be really great!
Driven by the frustration that I couldn't find a decent, simple, free online drawing tool to help with our building project.
Given time, I think it has the potential to be really great!
SimpleDraw is now live!
simpledraw.app/blog/simple-...
Simple, powerful, drawing app, in your browser. Create accurate drawings for renovation projects, garden planning, etc.
As easy as using pen & paper, but a great deal more flexible!
Free to use, no sign-up required.
simpledraw.app/blog/simple-...
Simple, powerful, drawing app, in your browser. Create accurate drawings for renovation projects, garden planning, etc.
As easy as using pen & paper, but a great deal more flexible!
Free to use, no sign-up required.
SimpleDraw
Simple, Accurate, Scale Drawing Made Easy
simpledraw.app
June 23, 2025 at 4:30 PM
Something I've been working on over the last couple of months.
Driven by the frustration that I couldn't find a decent, simple, free online drawing tool to help with our building project.
Given time, I think it has the potential to be really great!
Driven by the frustration that I couldn't find a decent, simple, free online drawing tool to help with our building project.
Given time, I think it has the potential to be really great!
Sad to see Stack Overflow decline so fast.
I never found asking or answering questions on SO to be a particularly pleasant experience, but as a resource for passive consumption, it was (and still is) invaluable.
blog.pragmaticengineer.com/stack-overfl...
I never found asking or answering questions on SO to be a particularly pleasant experience, but as a resource for passive consumption, it was (and still is) invaluable.
blog.pragmaticengineer.com/stack-overfl...
Stack overflow is almost dead
Today, Stack overflow has almost as few questions asked per month, as when it launched back in 2009. A recap of its slow, then rapid, downfall.
blog.pragmaticengineer.com
May 17, 2025 at 11:02 AM
Sad to see Stack Overflow decline so fast.
I never found asking or answering questions on SO to be a particularly pleasant experience, but as a resource for passive consumption, it was (and still is) invaluable.
blog.pragmaticengineer.com/stack-overfl...
I never found asking or answering questions on SO to be a particularly pleasant experience, but as a resource for passive consumption, it was (and still is) invaluable.
blog.pragmaticengineer.com/stack-overfl...
Just discovered this
An extremely useful, thoughtfully developed set of resources on the many challenges and issues presented by the proliferation of LLMs.
An extremely useful, thoughtfully developed set of resources on the many challenges and issues presented by the proliferation of LLMs.
Modern-Day Oracles or Bullshit Machines?
Jevin West (@jevinwest.bsky.social) and I have spent the last eight months developing the course on large language models (LLMs) that we think every college freshman needs to take.
thebullshitmachines.com
Jevin West (@jevinwest.bsky.social) and I have spent the last eight months developing the course on large language models (LLMs) that we think every college freshman needs to take.
thebullshitmachines.com
INTRODUCTION
thebullshitmachines.com
May 17, 2025 at 10:57 AM
Just discovered this
An extremely useful, thoughtfully developed set of resources on the many challenges and issues presented by the proliferation of LLMs.
An extremely useful, thoughtfully developed set of resources on the many challenges and issues presented by the proliferation of LLMs.
Thoughtful post about the issues that arise with agentic coding.
An interesting question IMO is to what extent multi-agent flows with tailored prompts per-role can mitigate these effects.
Due to its openness, RooCode seems to be the best currently available tool for this kind of experimentation.
An interesting question IMO is to what extent multi-agent flows with tailored prompts per-role can mitigate these effects.
Due to its openness, RooCode seems to be the best currently available tool for this kind of experimentation.
NEW POST
To work effectively with agentic coding assistants, Birgitta Böckeler found she needs to intervene, correct and steer all the time. She describes examples of these interventions indicating the skills we need to correct the tools' missteps
martinfowler.com/articles/exp...
To work effectively with agentic coding assistants, Birgitta Böckeler found she needs to intervene, correct and steer all the time. She describes examples of these interventions indicating the skills we need to correct the tools' missteps
martinfowler.com/articles/exp...
April 6, 2025 at 4:45 PM
Thoughtful post about the issues that arise with agentic coding.
An interesting question IMO is to what extent multi-agent flows with tailored prompts per-role can mitigate these effects.
Due to its openness, RooCode seems to be the best currently available tool for this kind of experimentation.
An interesting question IMO is to what extent multi-agent flows with tailored prompts per-role can mitigate these effects.
Due to its openness, RooCode seems to be the best currently available tool for this kind of experimentation.
Open Router shows 1.35T tokens from AI coding tools Cline and Roo this month.
Easily 75% of this is waste, because client-side tooling is ineffective at concisely providing LLMs with relevant context.
That's 1T tokens/month of pure waste - and that's just the traffic passing through Open Router.
Easily 75% of this is waste, because client-side tooling is ineffective at concisely providing LLMs with relevant context.
That's 1T tokens/month of pure waste - and that's just the traffic passing through Open Router.
March 18, 2025 at 7:35 PM
Open Router shows 1.35T tokens from AI coding tools Cline and Roo this month.
Easily 75% of this is waste, because client-side tooling is ineffective at concisely providing LLMs with relevant context.
That's 1T tokens/month of pure waste - and that's just the traffic passing through Open Router.
Easily 75% of this is waste, because client-side tooling is ineffective at concisely providing LLMs with relevant context.
That's 1T tokens/month of pure waste - and that's just the traffic passing through Open Router.
When I switched to using Cline (and then Roo) for AI coding, I realized how rapidly my LLM's context window was filling up.
An LLM chewing through an entire module just to see what's happening in a few lines of code is supremely wasteful.
github.com/buger/probe is going to help change that.
An LLM chewing through an entire module just to see what's happening in a few lines of code is supremely wasteful.
github.com/buger/probe is going to help change that.
March 18, 2025 at 7:19 PM
When I switched to using Cline (and then Roo) for AI coding, I realized how rapidly my LLM's context window was filling up.
An LLM chewing through an entire module just to see what's happening in a few lines of code is supremely wasteful.
github.com/buger/probe is going to help change that.
An LLM chewing through an entire module just to see what's happening in a few lines of code is supremely wasteful.
github.com/buger/probe is going to help change that.
Asked GPT-4o-mini to analyse a business idea.
It's response was reasonable, coherent, but also utterly generic and bland, and contained nothing that was in any way thought provoking.
Then I tried asking GPT-4.5-preview...
Just one question cost me $0.50, but its response was absolute 🔥
It's response was reasonable, coherent, but also utterly generic and bland, and contained nothing that was in any way thought provoking.
Then I tried asking GPT-4.5-preview...
Just one question cost me $0.50, but its response was absolute 🔥
March 14, 2025 at 12:41 PM
Asked GPT-4o-mini to analyse a business idea.
It's response was reasonable, coherent, but also utterly generic and bland, and contained nothing that was in any way thought provoking.
Then I tried asking GPT-4.5-preview...
Just one question cost me $0.50, but its response was absolute 🔥
It's response was reasonable, coherent, but also utterly generic and bland, and contained nothing that was in any way thought provoking.
Then I tried asking GPT-4.5-preview...
Just one question cost me $0.50, but its response was absolute 🔥
If you ever wanted to listen to an upbeat podcast about an obscure github project that you've personally put many hours of work into....
www.gitpodcast.com
It's very obviously artificial, and makes some odd choices about what to focus on.
Nevertheless, it's surprisingly uplifting and validating!
www.gitpodcast.com
It's very obviously artificial, and makes some odd choices about what to focus on.
Nevertheless, it's surprisingly uplifting and validating!
March 13, 2025 at 1:36 PM
If you ever wanted to listen to an upbeat podcast about an obscure github project that you've personally put many hours of work into....
www.gitpodcast.com
It's very obviously artificial, and makes some odd choices about what to focus on.
Nevertheless, it's surprisingly uplifting and validating!
www.gitpodcast.com
It's very obviously artificial, and makes some odd choices about what to focus on.
Nevertheless, it's surprisingly uplifting and validating!