Sunday, November 2, 2025

How I use every Claude Code feature

How I use every Claude Code feature
384 by sshh12 | 141 comments on Hacker News.


Show HN: Why write code if the LLM can just do the thing? (web app experiment)

Show HN: Why write code if the LLM can just do the thing? (web app experiment)
361 by samrolken | 258 comments on Hacker News.
I spent a few hours last weekend testing whether AI can replace code by executing directly. Built a contact manager where every HTTP request goes to an LLM with three tools: database (SQLite), webResponse (HTML/JSON/JS), and updateMemory (feedback). No routes, no controllers, no business logic. The AI designs schemas on first request, generates UIs from paths alone, and evolves based on natural language feedback. It works—forms submit, data persists, APIs return JSON—but it's catastrophically slow (30-60s per request), absurdly expensive ($0.05/request), and has zero UI consistency between requests. The capability exists; performance is the problem. When inference gets 10x faster, maybe the question shifts from "how do we generate better code?" to "why generate code at all?"

Visopsys: OS maintained by a single developer since 1997

Visopsys: OS maintained by a single developer since 1997
337 by kome | 64 comments on Hacker News.