Cool! I was excited when I saw this and signed up.
One key thing I was hoping for was a consistent resync with source material particularly google docs. Looks like I'll have to download then upload to your app whenever they change.
Yes this sounds very useful and productive. Having project context updated based on external events. I will share it on socials when ready, thanks for the feedback!
Will replicache be deprecated? Or continue to be developed/supported? E.g. Partial downloads aren't really necessary in our case so Zero isn't really necessary (although it is cool!).
I hesitate to use the word 'deprecated' because it means different things to different people. We'll continue supporting Replicache but won't add new features to it.
Even if you don't think you'll need partial sync our experience is that almost all projects end up needing either it or permissions. Both of which are difficult with Replicache.
And if you don't need either of those, the the query-based programming model of Zero is just a lot more fun.
Cool! It would be nice to use this to quickly iterate on the prompts I plan to use within https://app.habitstack.com. Basically, supply the user input in the query string and get back the result. Then in Pancaik see the log of combined prompts, the results, and be able to fine tune the prompts over time. Any plans to go that direction?
Yes, I have plans to log user provided inputs and the responses from GPT. You can monitor these inputs/responses to see if the responses that are coming back are of high quality. If it feels like you can improve the prompt, you will be able to use a prompt engineering tool which will let you experiment with different prompts and run them against a bunch of user inputs. You can then compare the new responses to the old ones and see if it's an improvement.
If you're thinking of integrating into another app, one of the next steps is to be able to take the AI web app you built and turn it into a component that you can put into your own websites/web apps. Also, at this point, you will be able to have inputs that are not just user provided, but can also come from your website/web app (e.g. data from your database).
This is an important observation. Most productivity apps don't end up "working" because they vastly underestimate the complexity of the problem they are trying to solve.
We need to do a far better job of addressing the psychology of self-improvement, one of the most important aspects being how to deal with the inevitable "falling off the wagon".
As you describe well, a naive approach to productivity tends to work at first, but then, as soon as you disengage for a time, they actively work _against_ re-engagement.
I think there is a lot to be figured out in this area.
One other related point is that although an app can't "solve the problem of self-discipline" it _can_ reduce the amount of energy required to "do the right thing" (e.g. by providing a easy to follow system). Since willpower requires energy which is a limited resource, this leaves more of it to apply towards continuing to work towards a goal instead of figuring out how to configure a goal achievement system.
I think you've nailed it. There are very few tools that help you connect the long term with the current week and day, at least in a meaningful way.
https://www.habitstack.com/ is geared towards this. You enter your goals for the year and chunk them down to the quarter, month, and week. Then the software prompts you to stay engaged with the system.
As Scott Adams wrote, "Losers have goals, winners have systems." :)
I'm the founder. Happy to dialogue about the future of productivity and goal setting any time!
I am not the author you are replying to but the grandparent. I thought of pricing for my system the same way.
If your productivity isn't worth 45 a month then this isn't the app for you. On the flip side, if this app makes you one percent more efficient then you generate thousands or millions of dollars in additional value, the price is well worth it.
That price, combined with the fact that pricing comes first in the menu is just off-putting. It seems to be more focused on extracting money than on being an actual good product. Signing up and seeing it just confirmed that for me. It's not even optimized for mobile screens.
I'd be fine to pay such amount if the app was polished and had great UX. Not arguing with what you stated.
Seems like this is a common thing people need and I too tried to make an app for this. I gave up on it because the complexity grew fast, but my plan was to release it for free and have some sort of premium. I wanted to have a good product first before asking for money.
HabitStack founder here. Your points are well taken! For some context, for the last few years, we've been a service company with a software product. You're seeing us at an awkward transition point to a product first company. So, sorry for the rough edges in the app! We're excited smooth them out.
What jumped out at you as needing immediate attention?
Yeah, we wrote special code to fix cut and pasting of bullets in some browsers like Chrome; however, recent versions of Chrome seem to fix this so we removed that code. We'd like to take credit for being the only WYSIWYG editors that fixes the cut/paste bullet problem but WebKit seems to have fixed that for all editors now.
We do the pricing by developer to differentiate between small websites (with 1 or 2 developers) from companies that are building SAAS apps with perhaps a dozen or more developers.
One key thing I was hoping for was a consistent resync with source material particularly google docs. Looks like I'll have to download then upload to your app whenever they change.
Is that right? Auto syncing in the plan?