Hacker News with Generative AI: Coding

Claude 4 (anthropic.com)
Today, we’re introducing the next generation of Claude models: Claude Opus 4 and Claude Sonnet 4, setting new standards for coding, advanced reasoning, and AI agents.

Generative AI, AI Agents, Coding, Reasoning

1912 points by meetpateltech 1 day ago | 1105 comments

GitHub Copilot: Meet the new coding agent (github.blog)
We are excited to introduce a new coding agent for GitHub Copilot. Embedded directly into GitHub, the agent starts its work when you assign a GitHub issue to Copilot or prompt it in VS Code. The agent spins up a secure and fully customizable development environment powered by GitHub Actions.

GitHub, Coding, AI, Tools, Software

9 points by meetpateltech 4 days ago | 0 comments

Vibe Check: Codex – OpenAI's New Coding Agent (every.to)
Last night I shipped a new feature for Cora, Every’s AI-enabled email assistant. Cora is not a vibe-coded product: Its codebase is a 5,500-plus commit cathedral of Rails craftsmanship mostly from Kieran Klaassen, Cora’s general manager, our resident DHH. Needless to say, exactly zero previous commits are mine.

OpenAI, Coding, Artificial Intelligence, Programming, Software

5 points by Philpax 7 days ago | 1 comments

Perverse incentives of vibe coding (medium.com)
I’ve been using AI coding assistants like Claude Code for a while now, and I’m here to say (with all due respect to people who have substance abuse issues), I may be an addict. And boy is this is an expensive habit.

AI, Coding, Addiction, Productivity

206 points by laurex 9 days ago | 227 comments

Quantifying AI Coding Impact (adamferrari.substack.com)
In an interview at Meta's recent LlamaCon, Microsoft chief Satya Nadella casually dropped some major bombs about the level of impact AI coding assistants are having at his company.

Artificial Intelligence, Coding, Business, Microsoft

15 points by gailaxelrod 9 days ago | 0 comments

Refactoring Agent for Bad Coders (github.com/bkidd1)

Software, Refactoring, Coding, Programming

6 points by BrinleeKidd 14 days ago | 0 comments

Ask HN: Privacy concerns when using AI assistants for coding? (ycombinator.com)
I've recently seen some teams claim to use third-party AI assistants like Claude or ChatGPT for coding. Don't they consider it a problem to feed their proprietary commercial code into the services of these third-party companies?

Privacy, AI, Coding, Software Development

6 points by Kholin 15 days ago | 6 comments

I so hate the phrase "vibe coding" (artiss.blog)

Coding, Tech Culture, Opinions

58 points by cumo 17 days ago | 65 comments

Vibe Coding Is Overrated (transitions.substack.com)
Vibe coding is on the rise. The term, popularized by Andrej Karpathy, describes the act of coding by simply uttering commands to AI assistants like Cursor.

AI, Coding, Software Development

45 points by cumo 20 days ago | 88 comments

The secret recipe of powerful AI coding Agents (medium.com)
The latest Black Mirror season is on brand — dystopian, twisted, and sometimes downright harsh in its commentary about the intersection of the human condition with technology. Throw in a good measure of dark humor sprinkled around moments when you least expect and you have a binge-worthy mind-bender on your hands.

Artificial Intelligence, Coding, Technology, Dystopia, Media

13 points by ghuntley 21 days ago | 0 comments

The Craft 001: A conversation about craft, code, and freedom with Neal Agarwal (workingtheorys.com)
In the age of slop, craft is rebellion.

Coding, Freedom, Creativity, Interviews

47 points by gripewater 21 days ago | 1 comments

I just want to code (2023) (zachbellay.com)
I have an angel and a devil sitting atop each shoulder. The angel says, "Just code for fun! What you make can be just for your enjoyment and that's --" the devil interjects, "not enough to get ahead, loser. If you're not coding your next startup then how're you gunna get rich? Coding for fun? Pfft, sounds like the fast lane to being poor."

Coding, Motivation, Software Development, Personal Development

288 points by SCUSKU 26 days ago | 172 comments

Anthropic sent takedown notice to dev trying to reverse-engineer its coding tool (techcrunch.com)
In the battle between two “agentic” coding tools — Anthropic’s Claude Code and OpenAI’s Codex CLI — the latter appears to be fostering more developer goodwill than the former.

Generative AI, Coding, Legal, Open Source, Competition

24 points by smusamashah 27 days ago | 10 comments

Avoiding skill atrophy in the age of AI (addyo.substack.com)
The rise of AI assistants in coding has sparked a paradox: we may be increasing productivity, but at risk of losing our edge to skill atrophy if we’re not careful. Skill atrophy refers to the decline or loss of skills over time due to lack of use or practice.

Artificial Intelligence, Coding, Skills, Productivity

373 points by NotInOurNames 28 days ago | 317 comments

Coding as Craft: Going Back to the Old Gym (cekrem.github.io)
Recently, Shopify’s CEO Tobi Lütke shared his thoughts on AI’s role in coding, stating that “reflexive AI usage is now a baseline expectation at Shopify.”

Coding, Software Development, Artificial Intelligence, Programming

98 points by codeman001 31 days ago | 93 comments

Ultrathink is a Claude Code magic word (simonwillison.net)
Claude Code: Best practices for agentic coding (via) Extensive new documentation from Anthropic on how to get the best results out of their Claude Code CLI coding agent tool, which includes this fascinating tip:

Coding, Artificial Intelligence, Programming Tools

113 points by ghuntley 34 days ago | 39 comments

We benchmarked GPT-4.1: it's better at code reviews than Claude Sonnet 3.7 (qodo.ai)
As AI coding assistants continue to evolve, one of the most relevant questions today is: which model provides the most helpful, precise, and actionable feedback for developers?

Generative AI, Software, Coding, Benchmarking

3 points by simplesort 39 days ago | 0 comments

How we learned to stop worrying and love the AI (in coding interviews) (assembled.com)

Artificial Intelligence, Coding, Interviews

16 points by johnjwang 44 days ago | 0 comments

Sculptor: Catch and fix issues as you code (imbue.com)
Sculptor is the first coding agent environment that helps you embed software engineering best practices.

Software Engineering, Tools, Coding, Software Development, Artificial Intelligence

61 points by thejash 45 days ago | 3 comments

Ask HN: Are You Vibe Coding? (ycombinator.com)
Are You Vibe Coding?

Software Development, Coding, Work Habits, Productivity

13 points by vibe_coding 53 days ago | 24 comments

Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison (composio.dev)
Google just launched Gemini 2.5 Pro on March 26th, claiming to be the best in coding, reasoning and overall everything. But I mostly care about how the model compares against the best available coding model, Claude 3.7 Sonnet (thinking), released at the end of February, which I have been using, and it has been a great experience

Coding, Generative AI, AI Comparison

483 points by mraniki 53 days ago | 328 comments

There is no Vibe Engineering (serce.me)
You've probably heard about "vibe coding" by now. The term was recently coined by Andrej Karpathy in his tweet. Andrej defines Vibe Coding as "a new kind of coding, where you fully give in to the vibes, embrace exponentials, and forget that the code even exists". The key difference between vibe coding and normal coding is that the engineer doesn’t interact with the codebase directly, and instead converses with the agent and inspects the final outcome.

Software Engineering, AI, Coding

71 points by todsacerdoti 53 days ago | 67 comments

Vibe Coding and Kodak Cameras (stevedylan.dev)
I’m sure many who read this are familiar by now with the term “vibe coding,” a euphoric style of programming where you prompt AI models or IDEs to write software and just “vibe.”

Coding, Artificial Intelligence, Programming, Software Development

3 points by jhunter1016 53 days ago | 0 comments

DeepSeek V3 0324 outpaces GPT 4.5 and Claude 3.7 in coding, other benchmarks (huggingface.co)
DeepSeek-V3-0324 demonstrates notable improvements over its predecessor, DeepSeek-V3, in several key aspects.

Generative AI, Benchmarking, Coding

7 points by xianshou 58 days ago | 0 comments

Not all AI-assisted programming is vibe coding (but vibe coding rocks) (simonwillison.net)
Vibe coding is having a moment. The term was coined by Andrej Karpathy just a few weeks ago (on February 6th) and has since been featured in the New York Times, Ars Technica, the Guardian and countless online discussions.

Artificial Intelligence, Programming, Coding, Trends

14 points by ingve 65 days ago | 0 comments

AI Blindspots – Blindspots in LLMs I've noticed while AI coding (ezyang.github.io)
Blindspots in LLMs I’ve noticed while AI coding.

Artificial Intelligence, Coding, Software Development

577 points by rahimnathwani 65 days ago | 240 comments

Building Agentic Flows with LangGraph and Model Context Protocol (qodo.ai)
In the newly released 1.0 version of Qodo Gen, our IDE plugin for AI coding and testing, we introduce agentic workflows that let AI make dynamic decisions to navigate complex coding tasks.

AI, Coding, Programming, Workflows, Software Development

18 points by gronky_ 66 days ago | 1 comments

Cursor told me I should learn coding instead of asking it to generate it (cursor.com)

Artificial Intelligence, Programming, Coding

658 points by nomilk 71 days ago | 399 comments

Reflection – AlphaGo / Gemini team building superintelligent coding agents (reflection.ai)
Reflection is an AI company building superintelligent autonomous systems.