Yash_sinha

Yash_sinha

UI/UX meets AI-powered product building

About

A community for exploring UI/UX design, AI tools, vibe coding, and prompt-driven product building — from early ideas to real digital products.

Badges

Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Forums

•

1d ago

AntFabric - Connect your teams, knowledge, and AI agents.

AntFabric by GeekyAnts brings chat, meetings, tasks, and AI agents into one workspace. It connects company knowledge with business systems to support everyday workflows, with access controls, audit trails, and human approvals built into the process.
•

2d ago

app store rejections are quietly killing vibe coded apps, anyone else seeing this?

I ve been building in the react native ecosystem for years (nativebase, gluestack) and lately im noticing a pattern. people generate a working app with AI over a weekend then get stuck for weeks at submission

Apple enforcing guideline 2.5.2, provisioning profiles, metadata rejections, the minimum functionality flag... the last mile just hasnt caught up with how fast the first mile got

few questions for folks here

•

3mo ago

Your AI coding tool keeps spawning clones of itself. Here's what that button actually does

If you use any of the current coding agents you've seen it: you ask where something lives in the codebase, the tool announces it's "spawning an explore agent", goes quiet for a minute, and comes back with a tidy two-sentence answer. The feature usually gets explained as teamwork, which hides the useful part.

The clone is a disposable context window. Your agent's memory is finite and expensive everything it reads stays in its working memory and gets re-billed on every turn after. So instead of reading 60 files into its own head, it forks a copy. The copy reads the 60 files (59 of which turn out to be dead ends), reports back two sentences, and gets deleted. The dead ends never touch your main session. That's the entire feature, and most of what people call "multi-agent" is this trick applied repeatedly.

The catch: the clone knows nothing you didn't write down. It can't see your conversation. The library you rejected an hour ago, the API version you're pinned to, the thing your teammate said in standup all invisible unless the delegation prompt spells them out. Which is why fan-out works great for reading and searching, and keeps failing for parallel writing: two clones writing code make small conflicting decisions about naming, style, and edge cases, nobody wrote the assumptions down, and the merge is where it dies.

Cost reality check, since this is the part nobody quotes: Anthropic's engineering blog put agents at roughly 4x the tokens of a chat session, and multi-agent systems at roughly 15x. Parallel intelligence is something you buy. A deep audit of an unfamiliar codebase can be worth 15x. A typo fix can't.

View more