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.
Claude Code rules everything around me.
July 10, 2025 at 1:35 PM
Claude Code rules everything around me.
The only thing stopping us from having autonomously self improving apps is the economics of tokens. But it will certainly happen. The fact that these things can via playwright mcp and/or unit tests actually make changes that don’t break stuff is going to make way for that autonomy.
July 4, 2025 at 4:48 PM
The only thing stopping us from having autonomously self improving apps is the economics of tokens. But it will certainly happen. The fact that these things can via playwright mcp and/or unit tests actually make changes that don’t break stuff is going to make way for that autonomy.
Companies use proprietary data for AI advantage. As individuals, we should too.
We now have the tools to synthesize our own data like never before.
saadiq.xyz/building-you...
What's your biggest "I know I wrote something about this somewhere" challenge?
#AIContext
We now have the tools to synthesize our own data like never before.
saadiq.xyz/building-you...
What's your biggest "I know I wrote something about this somewhere" challenge?
#AIContext
Building Your Personal Data Pipeline: Taking Control of Your AI Context
Companies leverage proprietary data for AI advantage. As individuals, we should too. I'm building my own personal data pipeline to make all my scattered context (notes, conversations, insights) search...
saadiq.xyz
July 3, 2025 at 1:00 PM
Companies use proprietary data for AI advantage. As individuals, we should too.
We now have the tools to synthesize our own data like never before.
saadiq.xyz/building-you...
What's your biggest "I know I wrote something about this somewhere" challenge?
#AIContext
We now have the tools to synthesize our own data like never before.
saadiq.xyz/building-you...
What's your biggest "I know I wrote something about this somewhere" challenge?
#AIContext
AI isn't just faster. It makes the impossible possible for resource-constrained orgs.
Small consultancies now offer enterprise research. Bootstrapped startups run agency campaigns. The winners: nimble players freed from past constraints.
Full post: saadiq.xyz/how-ai-chang...
Small consultancies now offer enterprise research. Bootstrapped startups run agency campaigns. The winners: nimble players freed from past constraints.
Full post: saadiq.xyz/how-ai-chang...
How AI Changes What's Possible, Not Just What's Faster
AI isn't just making existing processes faster—it's enabling organizations to adopt capabilities they could never afford before. This creates leapfrog advantages for players previously locked out by r...
saadiq.xyz
June 5, 2025 at 2:00 PM
AI isn't just faster. It makes the impossible possible for resource-constrained orgs.
Small consultancies now offer enterprise research. Bootstrapped startups run agency campaigns. The winners: nimble players freed from past constraints.
Full post: saadiq.xyz/how-ai-chang...
Small consultancies now offer enterprise research. Bootstrapped startups run agency campaigns. The winners: nimble players freed from past constraints.
Full post: saadiq.xyz/how-ai-chang...
Any time I check out workflow automation tools like Zapier I always get stuck on having to learn THEIR way of constructing a program. Used to be worth it for the integrations but now... It's easier to have AI help me write code than it is to decipher their particular eccentricities.
June 3, 2025 at 1:53 AM
Any time I check out workflow automation tools like Zapier I always get stuck on having to learn THEIR way of constructing a program. Used to be worth it for the integrations but now... It's easier to have AI help me write code than it is to decipher their particular eccentricities.
AI as writer is hit and miss but AI as editor is not to be missed.
June 2, 2025 at 8:27 PM
AI as writer is hit and miss but AI as editor is not to be missed.
Now that anyone can mimic yesterday’s “perfect” style, the real question is which new styles will cut through the noise. I’m fine with em-dashes, but when every post starts to look the same, I can’t help craving something fresh.
June 2, 2025 at 12:58 PM
Now that anyone can mimic yesterday’s “perfect” style, the real question is which new styles will cut through the noise. I’m fine with em-dashes, but when every post starts to look the same, I can’t help craving something fresh.
Watching for the slow creep of markdown becoming a first class format for document tools everywhere. As AI becomes a dominant part of everyone's workflow, it's just going to be inescapably convenient. If you aren't aware, LLMs speak markdown. Doing more and more doc mgmt in Obsidian.md now.
Obsidian - Sharpen your thinking
The free and flexible app for your private thoughts.
Obsidian.md
May 28, 2025 at 3:43 PM
Watching for the slow creep of markdown becoming a first class format for document tools everywhere. As AI becomes a dominant part of everyone's workflow, it's just going to be inescapably convenient. If you aren't aware, LLMs speak markdown. Doing more and more doc mgmt in Obsidian.md now.
New model day is like Christmas. What previously impossible thing is now absolutely mundane?!?
May 22, 2025 at 5:57 PM
New model day is like Christmas. What previously impossible thing is now absolutely mundane?!?