"AI code = future revenue for the cybersecurity guy": Most devs aren't security experts anyway. It's a specialization. Both AI and human code benefit from security review. People judge quality by production mechanism out of unfamiliarity. AI can actually enforce security rules more consistently.
January 21, 2026 at 2:52 PM
"AI code = future revenue for the cybersecurity guy": Most devs aren't security experts anyway. It's a specialization. Both AI and human code benefit from security review. People judge quality by production mechanism out of unfamiliarity. AI can actually enforce security rules more consistently.
After Claude Code has figured out how to do something that you need to repeat, ask it to create a skill so that you don't have to watch it figure it out again from first principles.
Make sure you have "plugin-dev" plugin installed from the "claude-plugins-official" marketplace.
Make sure you have "plugin-dev" plugin installed from the "claude-plugins-official" marketplace.
January 19, 2026 at 7:16 PM
After Claude Code has figured out how to do something that you need to repeat, ask it to create a skill so that you don't have to watch it figure it out again from first principles.
Make sure you have "plugin-dev" plugin installed from the "claude-plugins-official" marketplace.
Make sure you have "plugin-dev" plugin installed from the "claude-plugins-official" marketplace.
Ownership has always been the the path to success.
What's different now is the lengths to which that can be taken. To play in spaces you're not fluent in in service of outcomes. To just do the thing instead of waiting for someone who can.
We have this power now. No excuse not to use it.
What's different now is the lengths to which that can be taken. To play in spaces you're not fluent in in service of outcomes. To just do the thing instead of waiting for someone who can.
We have this power now. No excuse not to use it.
January 16, 2026 at 1:50 PM
Ownership has always been the the path to success.
What's different now is the lengths to which that can be taken. To play in spaces you're not fluent in in service of outcomes. To just do the thing instead of waiting for someone who can.
We have this power now. No excuse not to use it.
What's different now is the lengths to which that can be taken. To play in spaces you're not fluent in in service of outcomes. To just do the thing instead of waiting for someone who can.
We have this power now. No excuse not to use it.
I realize that both the profile picture and the background image on this profile were from a trip to Iceland. I do not live in Iceland. I've visited 2x. But the accidental choice of nice and recent images is telling a very different story. 🤷♂️
January 12, 2026 at 12:48 PM
I realize that both the profile picture and the background image on this profile were from a trip to Iceland. I do not live in Iceland. I've visited 2x. But the accidental choice of nice and recent images is telling a very different story. 🤷♂️
I've previously been maintaing little repos of documents for projects and clients. Mostly markdown, of course. I then used VS Code to view, preview and edit files.
December 30, 2025 at 9:49 PM
I've previously been maintaing little repos of documents for projects and clients. Mostly markdown, of course. I then used VS Code to view, preview and edit files.
Archimedes: 'Give me a lever long enough and a fulcrum on which to place it, and I shall move the world.'
December 22, 2025 at 11:48 PM
Archimedes: 'Give me a lever long enough and a fulcrum on which to place it, and I shall move the world.'
How are you cleaning up the base context for your Claude Code projects? I recently cleaned up a bunch some stuff but still, a new session starts off with 34% of context used and I'm curious how others are managing this.
December 22, 2025 at 2:56 PM
How are you cleaning up the base context for your Claude Code projects? I recently cleaned up a bunch some stuff but still, a new session starts off with 34% of context used and I'm curious how others are managing this.
People who run an AI dev environment on top of an Obsidian vault, do you use source control on it? In any other context I have AI working I'll have git in the mix. But when I use it on Obsidian, I duplicate the repo before goign to work. Should my Obsidian vault be a git repo?
December 22, 2025 at 2:43 PM
People who run an AI dev environment on top of an Obsidian vault, do you use source control on it? In any other context I have AI working I'll have git in the mix. But when I use it on Obsidian, I duplicate the repo before goign to work. Should my Obsidian vault be a git repo?
All the platforms that were built for developers (API forward, CLI, customization and integrations) are smelling like daisies now. The promise of a community that can extend your platform has become even greater with the vibe coding army showing up.
December 19, 2025 at 3:13 PM
All the platforms that were built for developers (API forward, CLI, customization and integrations) are smelling like daisies now. The promise of a community that can extend your platform has become even greater with the vibe coding army showing up.
If you've been working with Claude Code for a little while, I highly recommend periodic context spring cleaning. Check out `/context` dig into the heavy weights. I had redundant elements in my CLAUDE.md, subagents that should now be skills and some that just need to go away. Safeguard that context.
December 17, 2025 at 6:40 PM
If you've been working with Claude Code for a little while, I highly recommend periodic context spring cleaning. Check out `/context` dig into the heavy weights. I had redundant elements in my CLAUDE.md, subagents that should now be skills and some that just need to go away. Safeguard that context.
Claude Code 2.0.65 adds context window info to the status line. Big recommend. Been hoping for this for a while.
Managing the context (all the junk in the chat thread) is key for better results.
Managing the context (all the junk in the chat thread) is key for better results.
December 11, 2025 at 2:28 PM
Claude Code 2.0.65 adds context window info to the status line. Big recommend. Been hoping for this for a while.
Managing the context (all the junk in the chat thread) is key for better results.
Managing the context (all the junk in the chat thread) is key for better results.
I frequently have to go from a markdown document into a Google Doc. The best way I have found is using VS Code to preview the markdown, changing the VS Code theme to "light mode" and then copying it into a fresh doc. Is there not a better way to carry over the formatting but nothing else?
December 10, 2025 at 7:00 PM
I frequently have to go from a markdown document into a Google Doc. The best way I have found is using VS Code to preview the markdown, changing the VS Code theme to "light mode" and then copying it into a fresh doc. Is there not a better way to carry over the formatting but nothing else?
Opus 4.5 being the current DEFAULT in Claude Code is wild. God bless VC cash and these companies lighting money on fire so I can play with new toys. 🫡
November 24, 2025 at 10:11 PM
Opus 4.5 being the current DEFAULT in Claude Code is wild. God bless VC cash and these companies lighting money on fire so I can play with new toys. 🫡
New model dropped. Time to build some stuff I didn’t even know I needed!
November 24, 2025 at 8:37 PM
New model dropped. Time to build some stuff I didn’t even know I needed!
If you put hand lotion on the bathroom sink, you are a monster. I will die on this hill.
Accidentally dispensing lotion when you were looking for soap is a violation.
Accidentally dispensing lotion when you were looking for soap is a violation.
November 19, 2025 at 5:41 PM
If you put hand lotion on the bathroom sink, you are a monster. I will die on this hill.
Accidentally dispensing lotion when you were looking for soap is a violation.
Accidentally dispensing lotion when you were looking for soap is a violation.
Anyone try Antigravity from Google? New AI-native IDE. Looks slick. New model looks amazing in my tests.
But really, the loyalty Claude Code is building via the skills setup is real. And sure, they are just markdown files. I could copy them over and use them manually. But who wants to do that?
But really, the loyalty Claude Code is building via the skills setup is real. And sure, they are just markdown files. I could copy them over and use them manually. But who wants to do that?
November 19, 2025 at 1:55 AM
Anyone try Antigravity from Google? New AI-native IDE. Looks slick. New model looks amazing in my tests.
But really, the loyalty Claude Code is building via the skills setup is real. And sure, they are just markdown files. I could copy them over and use them manually. But who wants to do that?
But really, the loyalty Claude Code is building via the skills setup is real. And sure, they are just markdown files. I could copy them over and use them manually. But who wants to do that?
It’s an interesting time to build a company. It’s both the best and worst time. We can build so much more but you have to keep racing to keep ahead of the avalanche of what is baked into the models.
November 15, 2025 at 5:47 PM
It’s an interesting time to build a company. It’s both the best and worst time. We can build so much more but you have to keep racing to keep ahead of the avalanche of what is baked into the models.
Vibe coding the app is fun. Vibe coding the analysis of your app is next level. I have all of these voice agent call logs to assess. Being able to extract and analyze those outcomes at scale is wild. Then to leverage the transcripts in my dev environment to iterate on future prompts... 🤌
November 14, 2025 at 3:06 PM
Vibe coding the app is fun. Vibe coding the analysis of your app is next level. I have all of these voice agent call logs to assess. Being able to extract and analyze those outcomes at scale is wild. Then to leverage the transcripts in my dev environment to iterate on future prompts... 🤌
I have a "writer's room" project in Claude Code to get feedback on my writing before I post. I think we may have over corrected on the sycophancy issue.
I'm BETTER THAN THAT?!? Claude, your words hurt, man. Your words hurt.
I'm BETTER THAN THAT?!? Claude, your words hurt, man. Your words hurt.
November 12, 2025 at 2:42 PM
I have a "writer's room" project in Claude Code to get feedback on my writing before I post. I think we may have over corrected on the sycophancy issue.
I'm BETTER THAN THAT?!? Claude, your words hurt, man. Your words hurt.
I'm BETTER THAN THAT?!? Claude, your words hurt, man. Your words hurt.
Want to understand where AI is headed? Stop reading. Start building.
The frontier is coding. Not because everyone needs to code. But because dev tools show you what's actually possible.
Building is what has given me all of my intuitions about how these things work and how to get the best results.
The frontier is coding. Not because everyone needs to code. But because dev tools show you what's actually possible.
Building is what has given me all of my intuitions about how these things work and how to get the best results.
November 6, 2025 at 6:08 PM
Want to understand where AI is headed? Stop reading. Start building.
The frontier is coding. Not because everyone needs to code. But because dev tools show you what's actually possible.
Building is what has given me all of my intuitions about how these things work and how to get the best results.
The frontier is coding. Not because everyone needs to code. But because dev tools show you what's actually possible.
Building is what has given me all of my intuitions about how these things work and how to get the best results.
The pervasiveness of "agents" reminds me of a conversation I had many years ago with an Indian friend about Starbucks' "Chai Tea Latte" triple redundancy.
Sadly, we live in a culture where if enough people are wrong, we don't try to educate them. Instead we update the dictionary. 😞 Literally.
Sadly, we live in a culture where if enough people are wrong, we don't try to educate them. Instead we update the dictionary. 😞 Literally.
October 30, 2025 at 3:08 PM
The pervasiveness of "agents" reminds me of a conversation I had many years ago with an Indian friend about Starbucks' "Chai Tea Latte" triple redundancy.
Sadly, we live in a culture where if enough people are wrong, we don't try to educate them. Instead we update the dictionary. 😞 Literally.
Sadly, we live in a culture where if enough people are wrong, we don't try to educate them. Instead we update the dictionary. 😞 Literally.
Return flight to JFK from SFO and the inflight internet has not been great on either leg. Trying to figure out if the connection has been "bad" or if the demands of a Claude Code driven workflow are video chat-esque in their consistency requirements to keep the tokens flowing.
October 25, 2025 at 4:52 PM
Return flight to JFK from SFO and the inflight internet has not been great on either leg. Trying to figure out if the connection has been "bad" or if the demands of a Claude Code driven workflow are video chat-esque in their consistency requirements to keep the tokens flowing.
It’s funny to start talking to Claude in story format. “As a coordinator, I need to be able to <> so that I can <>.” I guess it’s funnier it’s taken me this long. The structure exists for a reason.
September 15, 2025 at 2:48 PM
It’s funny to start talking to Claude in story format. “As a coordinator, I need to be able to <> so that I can <>.” I guess it’s funnier it’s taken me this long. The structure exists for a reason.
Reposted by Saadiq
It’s really wild the range of experiences with AI. Sometimes this thing is omniscient. Sometimes it really can’t see what’s right in front of its face. I get why non-technical people unfamiliar with AI have such a rough time. The "uneven frontier" is no joke.
July 11, 2025 at 3:14 PM
It’s really wild the range of experiences with AI. Sometimes this thing is omniscient. Sometimes it really can’t see what’s right in front of its face. I get why non-technical people unfamiliar with AI have such a rough time. The "uneven frontier" is no joke.