Alex

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.

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.

@Akasheth_ 2 of these are not frameworks 😭

What’s your go-to framework for app development?

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. x.com/OpenAI/status/…

If you could remove one thing that creates unnecessary friction in productivity apps, what would it be?

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.

seeing routines and tasks in chronological order changes the mental load immediately.

@colinhacks Does this work in GitLab?

introducing Pullfrog — the open source CodeRabbit alternative that runs in GitHub Actions 🐸 OSS 🐸 model-agnostic 🐸 transparent pricing: 7¢/run (plus model costs) 🐸 BYOK (or use our at-cost model router) 🐸 does PR review, issue triage, coding tasks, etc (just tag @ pullfrog)

What if we built better software, not just more of it?

@rezoundous how do you define AGI?

GPT-5.6 solves frontend design. GPT-6 AGI. Probably..

update on this since a lot of people seem to relate. i think i’ve 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. i’ve been trying out this app Utter(not affiliated) that was recommended in the comments and it’s been great so far. (gonna check out superwhisper too) took some fiddling to get it set up, but i’m 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 i’ve tried.

@TTrimoreau with the amount of time i get to actually work on my project, i rarely hit limits

@dev_alexandrum Don’t wanna go on max plan ?

Are you paying for Claude or Codex or maybe both?

@mackross i’ve seen that app featured in a @SnazzyLabs video recently. i thought it was just typing but maybe it has voice support too

Have an LLM clean up your thoughts (super whisper style). I feel like there is an app where when you start speaking a screenshot is taken for context, fed to an LLM to warm up the cache, used to pull out technical terms/names for improved transcription and then the transcription is rewritten in the context of the screen shot.

i feel like i don’t 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

@Jaytel just cancelled my subscription last week 💀 what am i missing?

I'd have never guessed that I'm back to using Cursor

@vikrambuilds you need to master the fundamentals of computer science/programming

Unpopular opinion: You don’t need to learn 10 new frameworks. You need to master prompting AI.

if no one ever saw it, would you still do it?

still not sure how to actually use remote control in Codex..

new week, what new tools are we using?

This

@bentlegen @mitchellh cool, i’ll check it out

@dev_alexandrum @mitchellh If you wanna try 0.12.0-beta.1 it should work if you set hunk as your pager

the @mitchellh effect