Latest Tech News

Stay updated with the latest in technology, AI, cybersecurity, and more

Filtered by: code Clear Filter

This Page Is a Quine (2021)

Hi, I'm Pranav And this page is a quine. What is that? Well, a quine is a program that produces its source code as its output. About me I am a research enginer at Conjecture, where you can find me tinkering with LLMs. You can find my resume here I started exploring computers when I was 7, when I got my hands on a QBASIC manual. I have loved writing code and computers ever since. I was a Google Code-in 2018 Grand Prize winner for my contributions to KDE Community, and was invited to visit Go

Microsoft Releases Historic 6502 Basic

Microsoft BASIC for 6502 Microprocessor - Version 1.1 Historical Significance This assembly language source code represents one of the most historically significant pieces of software from the early personal computer era. It is the complete source code for Microsoft BASIC Version 1.1 for the 6502 microprocessor, originally developed and copyrighted by Microsoft in 1976-1978. Why This Document is Historically Important 1. Foundation of the Personal Computer Revolution This BASIC interpreter

Writing a C compiler in 500 lines of Python

Writing a C compiler in 500 lines of Python Posted August 30, 2023 A few months ago, I set myself the challenge of writing a C compiler in 500 lines of Python , after writing my SDF donut post. How hard could it be? The answer was, pretty hard, even when dropping quite a few features. But it was also pretty interesting, and the result is surprisingly functional and not too hard to understand! There's too much code for me to comprehensively cover in a single blog post , so I'll just give an ove

Topics: code emit i32 lexer type

Claude Code: Now in Beta in Zed

You asked for it. A lot. So we built it: our Claude Code integration is now available in public beta, running natively in Zed through our new Agent Client Protocol (ACP). For months, developers have been asking us to bring Claude Code into Zed. We didn’t just want to bolt on a one-off integration; we wanted to build something better. ACP is our new open standard that lets any agent connect to Zed (and other editors, too). Claude Code is a perfect example of what’s possible. Now you can: Run

Topics: acp agent claude code zed

Warp brings new diff-tracking tools to the AI coding arms race

The AI coding tool Warp has a plan for making coding agents more comprehensible — and it looks an awful lot like pair programming. Today, the company is releasing Warp Code, a new set of features designed to give users more oversight over command-line-based coding agents, with more extensive difference tracking and a clearer view of what the coding agent is doing. “I feel like with these other command-line tools, you’re kind of just crossing your fingers and hoping that what comes out the othe

Exclusive: Nomad now 20% off sitewide for 9to5 readers – New Apple Watch bands, Find My card, MagSafe stands, more

Labor Day weekend might have already come and gone, but the big-time deals at Nomad are just starting now. We have now secured 9to5 readers a special code that will knock 20% off everything on the site, from its super-popular Find My Tracking Card and brand new Tempo Apple Watch bands through to iPhone/iPad cases, its premium MagSafe charging stations, and everything in between. Just use code 9to520 at checkout to slash 20% off your order. Nomad 20% off sitewide for 9to5 readers We have featur

10-20x Faster LLVM -O0 Back-End – Code Generation

5 years ago, @nikic wrote: I can’t say a 10% improvement is making LLVM fast again, we would need a 10x improvement for it to deserve that label. We recently open-sourced TPDE and our fast LLVM baseline back-end (TPDE-LLVM), which is 10-20x faster than the LLVM -O0 back-end with similar runtime performance and 10-30% larger code size. We support a typical subset of LLVM-IR and only target x86-64 and AArch64. Posting this here, as this might be interesting for the LLVM community – questions/com

Topics: 10 code ir llvm size

Parallel AI agents are a game changer

I’ve been in this industry long enough to watch technologies come and go. I’ve seen the excitement around new frameworks, the promises of revolutionary tools, and the breathless predictions about what would “change everything.” Most of the time, these technologies turned out to be incremental improvements wrapped in marketing hyperbole. But parallel agents? This is different. This is the first time I can say, without any exaggeration, that I’m witnessing technology that will fundamentally trans

Pearl – An Erlang lexer and syntax highlighter in Gleam

Pearl An Erlang lexer and syntax highlighter for Gleam! Pearl is a lexer and syntax highlighter for Erlang, written in Gleam. The lexer is based on glexer and just , allowing you to convert Erlang source code into tokens. There is also an API which allows you to highlight Erlang code using ansi colours, html or a custom format. Heavily inspired by contour . gleam add pearl@2 import pearl pub fn main ( ) { let code = " -module(hello). -export([hello_world/0]). hello_world() -> io:fwrite( \" H

A staff engineer's journey with Claude Code

Until 18 months ago, I wrote every line of code myself. Today, AI writes 80% of my initial implementations while I focus on architecture, review, and steering multiple development threads simultaneously. This isn't another "AI will change everything" post. This is about the messy reality of integrating AI into production development workflows: what actually works, what wastes your time, and why treating AI like a "junior developer who doesn't learn" became my mental model for success. The back

First attempt will be 95% garbage: 6 weeks with Claude Code

Until 18 months ago, I wrote every line of code myself. Today, AI writes 80% of my initial implementations while I focus on architecture, review, and steering multiple development threads simultaneously. This isn't another "AI will change everything" post. This is about the messy reality of integrating AI into production development workflows: what actually works, what wastes your time, and why treating AI like a "junior developer who doesn't learn" became my mental model for success. The back

I asked AI to modify mission-critical code, and what happened next haunts me

Tsuba_sa/iStock/Getty Images Plus Follow ZDNET: Add us as a preferred source on Google. ZDNET's key takeaways AI repeated major sections in a mission-critical coding plan. Mission-critical coding work is too risky to delegate to AI. AI is fine for new features, not core infrastructure. I woke up in a cold sweat. In my nightmare, I was being chased by tens of thousands of people, all of whom were enraged because I destroyed their privacy. They were all holding laptops over their heads, swin

Vibe coding as a VC

Those vacations were the most intense I’ve had in a while. Time off is always the chance to focus on building knowledge or skills, whether for personal enjoyment or for work. And this summer break was the perfect moment to disconnect from the hectic daily routine, the endless flow of emails and back-to-back meetings, and dive into introspection. Walk the Talk Our job is to look for AI-native companies (post-LLM startups), because we believe they are a different breed, born in a different world

Topics: ai claude code data time

A review of Nim 2: The good and bad with example code

I've been using Nim for about 1-2 years now, and I believe the language is undervalued. It's not perfect, of course, but it's pleasant to write and read. My personal website uses Nim. After reading a recent article on Nim ("Why Nim") and the associated HN comments, it's clear that comments and some information about Nim are misleading and outdated. Since Nim 2, a tracing Garbage Collector is not the default nor the recommended memory management option. Instead, the default memory management mod

De-Googling TOTP Authenticator Codes

Back to Articles 1st Sep 2025 In the ongoing effort to extricate myself from Google's services, I've been paring down my usage of their apps on my (admittedly Android) phone. I'm now down to two Google apps I use regularly: Maps (for traffic data) and Authenticator (for TOTP [A] Time-based One Time Password codes). Now, I spend most of my time in a terminal window on MacOS or connected to a Linux machine; it'd be nice if I could get TOTPs on the command-line, and it turns out there's a utilit

Bear is now source-available

Bear is now source-available 01 Sep, 2025 When I started building Bear I made the code available under an MIT license. I didn't give it much thought at the time, but knew that I wanted the code to be available for people to learn from, and to make it easily auditable so users could validate claims I have made about the privacy and security of the platform. Unfortunately over the years there have been cases of people forking the project in the attempt to set up a competing service. And it hurt

Anthropic is testing GPT Codex-like Claude Code web app

Anthropic is planning to bring the famous Claude Code to the web, and it might be similar to ChatGPT Codex, but you'll need GitHub to get started. For those unaware, Claude Code, which works with paid plans, is an AI-powered coding assistant that runs inside your terminal. It is primarily designed for developers, and it can understand the entire codebase of your app. Claude code in Windows Terminal Source: BleepingComputer With Claude Code, you can fix bugs, test new features, simplify Git o

OpenAI releases big upgrade for ChatGPT Codex for agentic coding

OpenAI has announced a big update for Codex, which is the company's agentic coding tool. The changes include new VS Code extension, sync support between web and terminal, and more. If you’ve a Plus or Pro subscription, you can now use Codex with every build, and it doesn’t matter where you use Codex. It now also works in your terminal or IDE. Codex has always supported web. Codex in Windows Terminal Source: BleepingComputer OpenAI states that your ChatGPT account connects it all, so you ca

Topics: code codex openai vs web

A Review of Nim 2: The Good and Bad with Example Code

I've been using Nim for about 1-2 years now, and I believe the language is undervalued. It's not perfect, of course, but it's pleasant to write and read. My personal website uses Nim. After reading a recent article on Nim ("Why Nim") and the associated HN comments, it's clear that comments and some information about Nim are misleading and outdated. Since Nim 2, a tracing Garbage Collector is not the default nor the recommended memory management option. Instead, the default memory management mod

Is AI the end of software engineering or the next step in its evolution?

The first time I used ChatGPT to code, back in early 2023, I was reminded of “The Monkey’s Paw,” a classic horror story about an accursed talisman that grants wishes, but always by the most malevolent path — the desired outcome arrives after exacting a brutal cost elsewhere first. With the same humorless literalness, ChatGPT would implement the change I’d asked for, while also scrambling dozens of unrelated lines. The output was typically over-engineered, often barnacled with irrelevant fragment

Topics: ai code coding like vibe

Show HN: Spotilyrics – See synchronized Spotify lyrics inside VS Code

See synchronized Spotify lyrics inside VS Code while coding. ✨ Features 📌 Live lyrics sync with your Spotify playback. with your Spotify playback. 🎨 Lyrics colors auto-themed from album cover (via colorthief ). ). 🖥️ Smooth side panel view – code on the left, lyrics on the right. – code on the left, lyrics on the right. 🔑 Simple one-time login using your own Spotify Client ID. using your own Spotify Client ID. 🚪 Quick logout command to reset session. 📸 Demo ⚡️ Installation Open VS Cod

Code Is Debt

“Tornike, what do you think of AI coding tools?” I like to answer this frequent question by way of an example. An example of two companies. It goes something like this: Imagine two very similar companies. Both companies generate similar revenue and produce a similar software product. The only difference between these companies is that Company A uses 1 million lines of code and Company B uses 100 thousand lines of code. Which company is better off? Clearly, the company with fewer lines of code

Vibe coding as a coding veteran: from 8-bit assembly to English-as-code

Note 1: On Tower of Hanoi Solutions and their Complexity. I chose the Tower of Hanoi puzzle (Lucas, 1883) because of its almost mythical status in computer science and discrete mathematics communities. It’s a staple in AI education and typically the first encounter with elegant doubly recursive algorithms for CS undergraduates. And, I chose the search algorithms mentioned in Section 1 because they constitute the core of the “state space search” paradigm in most AI textbooks (e.g., Chapters 3 and

10-20x Faster LLVM -O0 Back-End

5 years ago, @nikic wrote: I can’t say a 10% improvement is making LLVM fast again, we would need a 10x improvement for it to deserve that label. We recently open-sourced TPDE and our fast LLVM baseline back-end (TPDE-LLVM), which is 10-20x faster than the LLVM -O0 back-end with similar runtime performance and 10-30% larger code size. We support a typical subset of LLVM-IR and only target x86-64 and AArch64. Posting this here, as this might be interesting for the LLVM community – questions/com

Topics: 10 code ir llvm size

How is Ultrassembler so fast?

How is Ultrassembler so fast? Ultrassembler is a superfast and complete RISC-V assembler library that I'm writing as a component of the bigger Chata signal processing project. Assemblers take in a platform-dependent assembly language and output that platform's native machine code which runs directly on the processor. "Why would you want to do this?" you might ask. First, existing RISC-V assemblers that conform the the entirety of the specification, as and llvm-mc , ship as binaries that you r

Survey: a third of senior developers say over half their code is AI-generated

Fastly’s July 2025 survey of 791 developers found a notable difference in how much AI-generated code is making it into production. About a third of senior developers (10+ years of experience) say over half their shipped code is AI-generated — nearly two and a half times the rate reported by junior developers (0–2 years of experience), at 13%. “AI will bench test code and find errors much faster than a human, repairing them seamlessly. This has been the case many times,” one senior developer sai

Launch HN: VibeFlow (YC S25) – Web app generator with visual, editable workflows

Hi HN! We’re Alessia and Elia, the founders of VibeFlow ( https://vibeflow.ai ). VibeFlow lets semi-technical people (i.e. people with some technical skill but who are not professional programmers) build full-stack web apps from natural language prompts, while making the underlying business logic clear and editable as a visual workflow. Demo video: https://www.youtube.com/watch?v=-CwWd3-b1JI The problem we’re trying to solve: today, people who want to build apps without coding often have to sti

Older developers are down with the vibe coding vibe

For those who thought AI vibe coding was just for the youngsters, newly published research shows that developers with over 10 years of experience are more than twice as likely to do it. According to a July survey of 791 US developers from cloud services platform Fastly, around a third of senior developers with more than a decade of experience are using AI code-generation tools such as Copilot, Claude, and Gemini to produce over half of their finished software, compared to 13 percent for those d

Vibe Coding as a Coding Veteran. From 8-Bit Assembly to English-as-Code

Note 1: On Tower of Hanoi Solutions and their Complexity. I chose the Tower of Hanoi puzzle (Lucas, 1883) because of its almost mythical status in computer science and discrete mathematics communities. It’s a staple in AI education and typically the first encounter with elegant doubly recursive algorithms for CS undergraduates. And, I chose the search algorithms mentioned in Section 1 because they constitute the core of the “state space search” paradigm in most AI textbooks (e.g., Chapters 3 and