Jitendra Kumar

Jitendra Kumar

Senior Software Engineer at Google

About

Experienced software developer with a demonstrated history in backend development, holds a bachelor's degree in Computer Science and Engineering from Indian Institute of Technology Patna.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking

Forums

Vibecoding a Mac window fix: the AI wrote the code fast, macOS was the hard part

For years my Mac moved all my windows onto one monitor every time it woke up, unlocked or went back on the dock. I finally sat down with an AI to build a small menu bar fix for myself, and had something working in under 24 hours.
What surprised me was where the time went. The code came fast. Understanding what macOS actually does took the rest.
Sleep is a disconnect. Most external monitors drop their link when the Mac sleeps, so macOS moves their windows to a screen that's still there and never moves them back.
Identical monitors can look like the same monitor. Many report the same serial number, so "which screen was this window on?" is not a trivial question.
Saving on a timer is a trap. The obvious approach is to snapshot window positions every few seconds. But if a snapshot runs right after a wake, you save the mess macOS just made instead of your real layout.
None of that is in the code an AI gives you on the first try. You only learn it by living with the problem.
What platform quirk ate most of your time on something you vibecoded?

•

6d ago

Anyone using both Claude Code and Codex? How do you manage context?

I've been using Claude Code and Codex for product design and prototyping work, and lately I've been paying more attention to how quickly tokens get used up in both.

I often go back and forth on UI changes within the same conversation. As the work continues, the context gets longer, and I'm trying to find a more efficient way to manage it.

I've been looking into whether MCP tools or different workflows could help reduce token usage, but I'm not sure what actually makes the biggest difference.

I'm also curious if anyone here uses Claude Code and Codex together.

New guide: turn AI Context Flow into the shared brain for your AI agents

Hi everyone

One of our power users has been running his go-to-market with a team of Grok Bot agents, all plugged into the same AI Context Flow memory. We loved it so much that we rebuilt it, tested it, and wrote it up.

The setup in short:
One memory bucket per agent, shared with your Claude and ChatGPT chats
One Todoist board where every agent tracks its work
A "Human" label that makes agents stop and wait before anything goes out

Full step-by-step guide with prompts: https://plurality.network/blogs/...

View more