I was curious about the YC backing and realised that you're the founders of https://www.ztool.co. Did you pivot or is this a complementary prodcut to ztool? Would love to hear more about your journey :)
This is definitely more of a pivot, though the ZTool product also went through a few bigger iterations itself. I think my learnings from building and talking to users the last few months boil down to two main things that led me to work on autotab.
1. AI-generated software isn't ready for non-technical users. With ZTool I was initially focused on making it easy for people who don't know how to code to create automations. For the reasons we talked about above, I think having the model's output be code is best for now, so autotab is focused on users that can review and tweak Python code.
2. How you communicate intent matters. There is a surprising amount of mental work required to go from "this task is annoying" to creating a structured representation of it (c.f. the whole world of process automation). AI demos have focused on short prompts to communicate intent, but those don't work that well for more complex domains. Using the browser to communicate intent seems really powerful because it's so intuitive/familiar.
Thank you! :) You are absolutely right on pre-commit hooks. My experience with FOSS projects is that it's quite hard to get contributors to follow your style guides and/or opt-in to pre-commit hooks. In this case it's much easier to have things auto-fixed than telling people to please install your specific pre-commit framework. It's different if you have a well-defined team with onboarding procedures.
FWIW, you can keep using pre-commit hooks and then have autofix.ci enforce them: https://autofix.ci/setup#pre-commit. For git purists, there's always the option to squash when merging. :)
It would be interesting to see how the sentiment about crypto changed over time on HN. I'm sure there was time when people saw a lot of potential in crypto technologies. Subjectively, the sentiment has shifted completely towards negativity in the last 1-2 years.
The first time Bitcoin was posted it received no comments and barely any votes. The second time it received mixed feedback. It took about a year for it to get a decent sized thread.
For what it's worth, my sentiment is that crypto[currencies]/blockchain tech. is essential for the same reasons that I believe Tor and end to end encryption are essential.
I believe that it's also highly likely that like end-to-end encryption, most people will use some form of this technology (or things built on it) very regularly in future.
But it may turn out to be that like Tor, most people don't. That wouldn't make it any less important that it exists.
We're preparing to shut it down or keep it running on low infrastructure costs. And that's why I've slowly started looking for my next job (and considered the startup prematurely as failed in the context of that post).
Since the beginning of mobile apps people tried to build habit apps. What works best for me is just sticking to the 4 simple rules around building lasting habits from the book Atomic Habits:
1) make it obvious, (2) make it attractive, (3) make it easy, and (4) make it satisfying.
Now that I'm reading all these horrible experiences, I'm wondering why there isn't a review system for businesses where I can read about such issues? I guess Trustpilot has a rating for Airbnb, but it's not very well known. How else could we make other consumers aware of such cases?
