Raptor turns Claude Code into a general-purpose AI
2 points, 1 comments on Hacker News
Page 2 of 6 — 131 headlines
2 points, 1 comments on Hacker News
AI wrote your code, tests passed, you shipped it, and it broke in production. Here is why that keeps happening and how to actually fix it. Why It Happens?
A common statement in a number of LLM/AI policies regarding AI assisted contributions across open source projects is that the developer is "responsible" for their contribution even if it was made wholly or in part by AI. I understand in layman's terms what this means and I can guess at the inten...
3 points, 1 comments on Hacker News
1 points, 0 comments on Hacker News
3 points, 0 comments on Hacker News
We keep hearing that the latest LLMs are approaching AGI. The people who run the frontier labs are warning or hinting that soon all code will be written by models. Some argue that software engineering is about much more than just coding, but you don't need nearly as many people for those other ...
2 points, 0 comments on Hacker News
Use the latest MGM promo code CBSSPORTS to get $1,500 in bonus bets if your first bet loses for college football betting on Saturday
Sign up and bet with the latest FanDuel promo code on Sunday to get your bonus bets
1 points, 0 comments on Hacker News
Sign up and bet with the latest FanDuel promo code on Sunday to get your bonus bets
2 points, 0 comments on Hacker News
In every project, someone says it sooner or later: "we have too much technical debt. " Everyone agrees. Nobody asks how much.
A dead simple local audit trail for Claude Code tool calls. Energized by a rule-based risk analyser. Give it a llama-cpp compatible GGUF model and it will give you a second opinion on risk locally.
Every AI coding assistant wants your credit card. And your code. There's a third option, and it costs nothing: run the whole thing on your own computer.
1 points, 0 comments on Hacker News
I’ve been building Layerz, a visual builder for native UIKit iOS apps — no code, and it runs live with no build step. What’s different from the usual no-code/app-builder stuff: - It renders real UIKit components (not a web view or HTML wrapper), so previews behave like the real thing. - Action ...
We measured whether AI-written code is messier than human-written code, across 500 real bugs where a human fix already exists. Thirteen of the fourteen models we tested raised a function's complexity or added dead code more often than the person who fixed the same bug. One tied.
The system still runs the business. It is also on a version nobody supports, two people understand it, and the quote you got for replacing it came with the phrase feature parity and a timeline in years. This page is written from your side of that quote.
1 points, 0 comments on Hacker News
Discovered something very interesting by chance a few days ago, and thought it might be interesting for other people running dynamic workflows with claude code. The workflow scripts themselves are javascript. Claude code knows the format and it can make a tool that composes workflows instead of...
3 points, 1 comments on Hacker News
2 points, 1 comments on Hacker News