I program on the subway • Hacker News Board

Re: I program on the subway

#211

Post by chrischen » Mon, Dec 29, 2025, 8:39 AM UTC

llbbdd wrote: post #9

chrischen wrote: post #7

With coding agents AI almost never manually type code anymore. It would be great to have a code editor that runs on my phone so I can do voice prompts and let the coding agents type stuff for me.

I have been doing this with GitHub's copilot agent web interface on my phone; word-vomit voice prompt + instructions to always run the tests or take screenshots so I can evaluate the change works really well.

Was it the github issues copilot integration? I found that to be slow compared to natively running copilot in the IDE.

Re: I program on the subway

#212

Post by chrischen » Mon, Dec 29, 2025, 8:42 AM UTC

lbrito wrote: post #10

chrischen wrote: post #7

With coding agents AI almost never manually type code anymore. It would be great to have a code editor that runs on my phone so I can do voice prompts and let the coding agents type stuff for me.

That sounds awful

To be fair with the languages I use there are only a finite number of ways a particular line or even function can be implemented due to high level algebraic data structures and strict type checking. Business logic is encoded as data requirements, which is encoded into types, which is enforced by the type checker. Even a non-AI based system can technically be made to fill in the code, but AI system allows this to sort of be generalized across many languages that did not implement auto-complete.

Re: I program on the subway

#213

Post by jamespo » Fri, Jan 02, 2026, 11:36 PM UTC

ibejoeb wrote: post #184

jamespo wrote: post #169

Earlier quoted context omitted.

What's the source for this "successful interventions often lead to prosecutions"?

Actual events. Are you looking for examples? Off the cuff, in the past 2 years we've had 2 high-profile incidents: Jordan Williams and Daniel Penny.

How are you defining often there?