I wanted a proper personal site for years, but moving all my content would have taken me a month. With Claude I did it over the weekend.
25 years ago I coded every page of the huge government website by hands. I typed every <p> by hands across 300+ large pages, and the tables almost killed me.
Over the weekend I connected Claude to GitHub and Vercel. I moved everything from every archive I had to the right place. Claude even came up with a few cool ideas along the way. This process is so pleasant it is hard to stop thinking and doing improvements. AI definitely make us work more, but for me personally in a good way.
I deleted my @Medium account, shut down @ghost, wiped everything from other several very old places and got everything in order at mdubakov.me/en
This process is so pleasant it is hard to stop thinking and doing improvements (could not resist doing it till 11 pm on Sunday). AI definitely make us work more, but for me, personally, in a good way.
25 years ago I coded every page of the huge government website by hands. I typed every <p> by hands across 300+ large pages, and the tables almost killed me.
Over the weekend I connected Claude to GitHub and Vercel. I moved everything from every archive I had to the right place. Claude even came up with a few cool ideas along the way. This process is so pleasant it is hard to stop thinking and doing improvements. AI definitely make us work more, but for me personally in a good way.
I deleted my @Medium account, shut down @ghost, wiped everything from other several very old places and got everything in order at mdubakov.me/en
This process is so pleasant it is hard to stop thinking and doing improvements (could not resist doing it till 11 pm on Sunday). AI definitely make us work more, but for me, personally, in a good way.
0
0
12
558
My dream is to move @FiberyHQ into this destination
I'm now building an "improvements" feature into all of my personal vibecoded applications: a freeform text input that's hooked up to an agent that yolo implements whatever is submitted.
It's an interesting experience -- the activation energy barrier to sanding any rough edge or ature becomes extremely low. Someone else who uses one of the applications I created has already implemented 150 improvements over the course of a few days. This pattern feels like a new kind of tool -- liquid software? -- and every application that doesn't have this feature now has a slightly rigid and anachronistic flavor. Why can't I just tell it how I want it to be different?
Now, it's not obvious to me how this pattern can or should scale. Does it become unmaintainable after a while? (Maybe model intelligence improvement outstrips my feature appetite such that it's fine?) How does collaborative software work in this model? Can software designed this way be secure and reliable?
Whatever the larger questions about broader deployment, it definitely works great in a personal context. It reminds me a little of the visions of Lisp/Lisp machines, Smalltalk, and HyperCard -- systems that the user can take control of and modify. Those visions never quite worked, though: the vast majority of software today is not end-user modifiable in any useful way. So, while this "liquid" affordance is a very small touch, the way it changes one's relation to the software feels a bit transgressive and empowering in a Lickliderian and Engelbartian way.
2
0
1
298
‘Do you think it’s ready?’ I asked.
‘It’s perfect . . . a masterpiece.’
‘Do you think it’ll sell?’ I asked.
‘No fucking way.’
‘It’s perfect . . . a masterpiece.’
‘Do you think it’ll sell?’ I asked.
‘No fucking way.’
0
0
4
424
Michael Dubakov retweeted
The coding interview is dead, at least for my team at Anthropic. I've seen enough to know that it no longer provides signal. I removed it from loops this month.
I have a spicy, optimistic take - I think there's an opportunity for junior engineers: felixrieseberg.com/hunger-beats-t…
I have a spicy, optimistic take - I think there's an opportunity for junior engineers: felixrieseberg.com/hunger-beats-t…
640
1,541
15,527
2,807,834
good one
blog.alxgsv.com/challenge-is-g…
"Now I’m completely absorbed in thinking about what to do rather than whether I can do it."
blog.alxgsv.com/challenge-is-g…
"Now I’m completely absorbed in thinking about what to do rather than whether I can do it."
0
0
3
321
alifeengineered.substack.com/p/on-the-death… "You must stand behind every sentence. “Oh, AI wrote that, ignore it” is never an acceptable answer to a reviewer’s question."
1
0
1
323
Nice one, resonates with my feeling about product role after 20+ years in it. Generalize pain → find effective solution → Generalize solution
svpg.com/a-fresh-defini…
svpg.com/a-fresh-defini…
1
0
2
304
Very creative! I'll give Jason that for sure.
For years, maybe a decade, I've wanted to build a writing tool that just did a few things I couldn't find anywhere else.
A system that mimicked how I think when I write. A system that provided clear affordances, features, and places to do the things I wanted to do. A way to play writing it. A way to settle into just the right way to say something.
It never made sense to make it a 37signals product because it's not commercially viable, nor would it be worth pulling people off their other work to hack on this. Plus, it would have taken months the old way.
So this weekend I just made it myself, with Claude's help.
It's called Write_On and the short video walks you through it.
Essentially it's "alternative control" at the word, sentence, and paragraph level, plus a way to dim stuff back, and stash stuff near by. Not version control, but alternative control. You'll see what I mean when you watch the video below.
So here it is. Write_On.
1
0
0
355
One more release I proud of. So many possibilities now!
We release every week!
🔥 Custom Apps as Entity Views: design the entity page you actually need.
Describe the entity view you want, and AI builds it. Build a dashboard, a form, a view with custom layout and 3 columns, an interactive game.
1
0
6
391
OK, @AnthropicAI added collaborative docs. They are very basic so far, but it is easy to make them great fast. Next step is databases? What will remain of @NotionHQ then? 🤔
2
0
4
495
Every program attempts to expand until it can draw a pelican. Those programs which cannot so expand are replaced by ones which can
0
0
2
363
It's hilarious to see how politicians who know nothing about AI and exponents express their opinion about safety of AI progress. Peter principle at its best.
1
0
1
250
Spot on:
"In my opinion, shorter reasoning traces are a side effect of more “intelligent” or capable models that make fewer mistakes and can access more compute internally inside their architecture versus using a reasoning trace as a scratchpad. In a sense, the same is true for humans. During an in-person college math exam, a smart and well-prepared student likely requires less use of the notepaper and needs to backtrack less often, and so on."
"In my opinion, shorter reasoning traces are a side effect of more “intelligent” or capable models that make fewer mistakes and can access more compute internally inside their architecture versus using a reasoning trace as a scratchpad. In a sense, the same is true for humans. During an in-person college math exam, a smart and well-prepared student likely requires less use of the notepaper and needs to backtrack less often, and so on."
1
0
1
254
I used to always use long dash in my texts (—) since it is right, but now I have internal pressure to use short dash (-) to not look like I write my texts with AI. Weird times...
0
0
4
386
Malleable software = 80% solid bases + 20% custom code
mdubakov.me/malleable-soft…
mdubakov.me/malleable-soft…
0
0
11
655
I joined the productivity tools market in 2004 and observing its dynamics for 22 years now. From time to time I write a holistic "visionary" article. The last one was in 2019 when I bet on the no-code revolution. That bet aged so-so. Here is the new one.
1
6
10
797
Where is the productivity tools market heading?
Everyone wants the same territory, but each road is different. We can have high expression power with less invested time since AI shrinks building and configuration time (everybody can prompt).
Everyone wants the same territory, but each road is different. We can have high expression power with less invested time since AI shrinks building and configuration time (everybody can prompt).
1
0
0
125