Tim ChenHostThank you.
I'm glad to be here.
So why don't we start at the very beginning, even though that's not too, too long ago.
But, like, where did you get the idea for Paperclip? Where did it come from?
Yeah.
So I guess it started for me really around, like, let's say October or November, where I kind of felt, like a lot of people, this shift where programming was solved.
You know, I'm a programmer by trade, founder, but really just, like, identified as being a programmer, and then all of a sudden, the models really made this jump where they could program better than I could.
And there's a bit of a, like, identity crisis there, but at the same time, a bit of, like, elation to where I could do an enormous amount of work, right? Things that would be a weekend project, you could just do in, like, a second.
And so everyone really kind of felt that about the time.
What I really found was, like, I would have thirty Claude code tabs open, ten Codex tabs open, and I was making enormous strides.
I would make twenty times X more work than I could do before.
But then the cracks started to show because I, like, I couldn't actually remember what I was working on in all of those tabs.
Like, what would happen is, like, I would start writing scripts to, like, remind me of what was happening.
My computer would crash, and I'd lose all my tabs, and I couldn't remember what I was working on come Monday morning.
I, I would start to write scripts to manage my Claude code tabs, and I'd show up Monday morning.
They'd exhausted my subscription budget.
I had no idea where the tokens were spent.
I'd spent all my money, and I didn't know what anyone had done.
So it was probably around, like, I think December, if I have my timing right, that I'd started using one of the early versions of what became OpenClaw.
And it's just such a magical piece of software, right? Like, industry-defining, incredible piece of software.
But at the time, really, like, the first week was amazing, and the second week, things just started to kind of fall apart.
I would struggle to kind of keep my work organized in a really detailed way.
Like, for work that I was, like, personally accountable for, that my team was working on, where I was, like, have this rigorous development process, that where I needed to QA the work and do the same process every time, OpenClaw wasn't sufficient for that level of, like, detail and record keeping that I needed to have.
And so that was kinda where Paperclip came up with, is that, is that I used OpenClaw for a couple of weeks.
It started to sort of fall apart, forget things.
Thank you.
I'm glad to be here.
So why don't we start at the very beginning, even though that's not too, too long ago.
But, like, where did you get the idea for Paperclip? Where did it come from?
Yeah.
So I guess it started for me really around, like, let's say October or November, where I kind of felt, like a lot of people, this shift where programming was solved.
You know, I'm a programmer by trade, founder, but really just, like, identified as being a programmer, and then all of a sudden, the models really made this jump where they could program better than I could.
And there's a bit of a, like, identity crisis there, but at the same time, a bit of, like, elation to where I could do an enormous amount of work, right? Things that would be a weekend project, you could just do in, like, a second.
And so everyone really kind of felt that about the time.
What I really found was, like, I would have thirty Claude code tabs open, ten Codex tabs open, and I was making enormous strides.
I would make twenty times X more work than I could do before.
But then the cracks started to show because I, like, I couldn't actually remember what I was working on in all of those tabs.
Like, what would happen is, like, I would start writing scripts to, like, remind me of what was happening.
My computer would crash, and I'd lose all my tabs, and I couldn't remember what I was working on come Monday morning.
I, I would start to write scripts to manage my Claude code tabs, and I'd show up Monday morning.
They'd exhausted my subscription budget.
I had no idea where the tokens were spent.
I'd spent all my money, and I didn't know what anyone had done.
So it was probably around, like, I think December, if I have my timing right, that I'd started using one of the early versions of what became OpenClaw.
And it's just such a magical piece of software, right? Like, industry-defining, incredible piece of software.
But at the time, really, like, the first week was amazing, and the second week, things just started to kind of fall apart.
I would struggle to kind of keep my work organized in a really detailed way.
Like, for work that I was, like, personally accountable for, that my team was working on, where I was, like, have this rigorous development process, that where I needed to QA the work and do the same process every time, OpenClaw wasn't sufficient for that level of, like, detail and record keeping that I needed to have.
And so that was kinda where Paperclip came up with, is that, is that I used OpenClaw for a couple of weeks.
It started to sort of fall apart, forget things.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.