I'm building an iPhone app called Kai.
People burn mental energy on decisions that structure should handle for them.
Most days don't fall apart because we lack ambition. They fall apart because too much has to be re-decided from scratch.
That's the problem I'm obsessed with.
i find it helpful for feature planning on the go with codebase context.
also if i want it to start a new feature in a worktree or something.
i still review code and do manual testing on my computer
You can now use your ChatGPT subscription in the Zed agent, with the same usage and rate limits you benefit from in Codex directly. We're grateful that @openaidevs continues to support subscription-based access for third-party tools, even as others move toward usage-based billing.
Step away from your laptop. Keep building with Codex on your phone.
Codex keeps working on your computer, with your files and project context still in place.
Pocket-sized access. Full Codex working state.
https://t.co/vGsw5wnHnG
i think "habit tracker" and "to-do list" are both incomplete models for how people actually try to improve their lives.
most people are trying to build enough structure that they can stop thinking about the basics and focus on deep work.
One thing I keep coming back to while building Kai:
your day should look like an action plan.
not a pile of decisions waiting to be renegotiated.
but i can't decide which ui looks better
update on this since a lot of people seem to relate.
i think iโve found a solution to my problem.
the issue is not necessarily that i change my mind about implementation.
i feel pressure to speak the perfect prompt as soon as the mic turns on. this is because i was using 1 to 1 speech to text which transcrivbes everything.
what i really need is a post-processor that will take my ramblings, rewording, and filler words and distill it into an actionable prompt for the agent.
iโve been trying out this app Utter(not affiliated) that was recommended in the comments and itโs been great so far. (gonna check out superwhisper too)
took some fiddling to get it set up, but iโm using the free on device models and i had claude write a custom post-process prompt.
now, i feel like i can speak for however long i want and come out the other side with a polished prompt.
still adapting to using voice first, but this is much better than /voice in Claude Code or anything else iโve tried.
i feel like i donโt think linearly enough for speech to text prompting.
i frequently change wording as i write so the pressure of having to voice the right prompt first try is frustrating
i feel like i donโt think linearly enough for speech to text prompting.
i frequently change wording as i write so the pressure of having to voice the right prompt first try is frustrating
ultra fast voice & language models will be even more important for everyday work
use your voice to work, and immediately see the result live on your screen. go between apps, navigate complex interfaces, create custom interfaces to preview, all instant