LordBron
Joined 15 years ago
Karma
70
Submissions
19
Member since
Mar 10
Recent submissions
Comment · 2 months ago
Comment · 9 years ago
Seems pretty neat, but how do you communicate with Katella? Is it it's own chat system? Or integrated into slack, etc?
Comment · 11 years ago
I should've covered that more in my post. It was actually pretty shocking to talk tech with not only the lawyers, but also a judge.
Lawyers understand law. Plus, the lawyers of the Legal Service Aid organization serve those who cannot afford a lawyer. They're strapped for time, cash and energy. It doesn't make sense to expect them to also stay on top of technology.
They talked about what they would basically need in an app. Most of it was native features of both the iOS and Android platform. Therefore, we said, "Okay, we can build that in a day." And they didn't believe it.
Even when we demo'd and explained how it was all built in 24 hours, they were amazed that tech (when yielded by capable hands) could transform a phone into such a powerful tool for justice.
It was a real eye opener for us. It really got a fire going in us to help these people who spend their entire lives helping others less fortunate than them get a fair chance. We want to continue to build even more tools moving forward, that will hopefully make their lives easier.
Comment · 13 years ago
I thought about doing mockups for the post, but decided it was already long enough as it was. I may break each one down into mockups still though and post them.
Comment · 13 years ago
I agree with the others. I think it's still useful to share, because in order to implement I need to build an entire IDE just to implement my features. That's an awful lot of work to see a feature request implemented.
I do agree that implementers are good though. As I mention in the post, I do have one more idea that I didn't share that I am going to build. I'll comment here again when I'm ready to announce it.
Comment · 13 years ago
If you want testers, let me know or drop a comment with a link in the post. Don't bother trying to get the details right yourself, let the masses help make the decisions for you.
Comment · 13 years ago
I'm with you on the interoperability, if anyone in the world should understand and be 100% completely behind that, it should be coders and makers of code tools. If we don't demand it and require it, then it's pretty hopeless for the rest of the tech world.
Comment · 15 years ago
I tried to get my previous business partner to realize that, but he (like others) feel uncomfortable with the "luck" factor. I'm not because I realize I got lucky and thus have even greater reason to take advantage of it. :)
My new business partner is 100% on board to seeing and taking advantage of luck.
When I talk about my own flavor of "one thinking session, short task sessions", it takes into account exactly what you're asking. The thinking sessions write to a series of documents, throughout the session. So if I'm talking about how I want Claude to code or how I want it to think about my voice, it takes notes in these documents. Meaning, when I shut down that thinking session, it dies and all the in-memory context dies, BUT the important stuff it learned got saved to the docs. Those documents become the scaffolding of newer sessions. When I spin up a new thinking session, Claude reads that scaffolding first, then says "Okay, I know everything about you and your project. We left off with these three things, which do you want to work on today?" The chart on our stats page actually prints that trade: at 2.1x, a re-seat that costs ten turns of getting up to speed pays for itself after ten more turns of work. Past 180 turns, at 2.86x, after six. https://my-status.app/stats#aging
It's that same scaffolding that we saw creeping up over time in this bit: "the scaffolding trend (the cost of our own rules, creeping 87,999 → 92,619 → 93,809 across three seats)" That meant that over three sessions, my initial token count for "getting up to speed" increased by roughly 6K tokens. "Don't let me repeat myself." and "Don't try to make a new table for everything." and other such rules got added during those sessions and thus upped the token size of the scaffolding. But that was okay to me because it meant there was no penalty for me killing sessions.
Now, what's interesting is a couple of days ago Anthropic cut cache-read pricing by another 75% on Fable 5.1. That was sweet music to my ears, because they basically said, "The way you work is smart and we should reward that." LOL That's not what they really said, but that's how I read them. :)