sayzard2d ago

Wes Roth (@WesRoth)

애플이 인기 있는 AI 바이브 코딩 앱들의 App Store 업데이트를 비공개로 중단하고 있으며, 특히 Replit과 Vibecode에 대해 큰 UX 변경을 요구한 것으로 알려졌다. AI 앱 배포와 심사 정책에 영향을 줄 수 있는 중요한 변화다.

https://x.com/WesRoth/status/2034721571726630953

#apple #appstore #replit #aicode #vibecode

Wes Roth (@WesRoth) on X

Apple has quietly halted App Store updates for popular AI "vibe-coding" applications most notably the $9 billion startup Replit and mobile app builder Vibecode. After months of pushback, Apple is reportedly demanding major UX changes. Replit is being asked to force its

X (formerly Twitter)
sayzard4d ago

Github Awesome (@GithubAwesome)

Udit Goenka가 만든 새로운 Claude Code 스킬이 소개되었습니다. Andrej Karpathy의 자율 AI 워크플로를 모방해, 밤사이 반복적으로 코드 변경을 수행하고 테스트를 실행하며 성능 지표가 개선될 때만 변경을 유지합니다. 번들 사이즈 자동 축소 등 코드 개선을 자동화하는 도구로 사용 가능한 점이 핵심입니다.

https://x.com/GithubAwesome/status/2033748093707960397

#claude #autonomousai #aicode #devtools #andrejkarpathy

Github Awesome (@GithubAwesome) on X

Want Andrej Karpathy's autonomous AI workflow for your own code? You need this new Claude Code skill by Udit Goenka. It endlessly loops while you sleep: making changes, running tests, and keeping the code only if your metrics improve. Use it to automatically shrink bundle sizes,

X (formerly Twitter)
N-gated Hacker News5d ago
🚀✨ Breaking news: #Mistral launches #Leanstral, the "trustworthy" #vibecoding foundation that promises to eliminate the pesky human review process for AI-generated code... because who needs quality assurance when you've got "vibes"? 🙄🎉 In a genius move, revolutionize software engineering by releasing code agents that work like magic wands, making formal proofs as easy as waving goodbye to accountability. 🚀😜
https://mistral.ai/news/leanstral #AIcode #SoftwareEngineering #HackerNews #ngated
Leanstral: Open-Source foundation for trustworthy vibe-coding | Mistral AI

First open-source code agent for Lean 4.

sayzardMar 15

Github Awesome (@GithubAwesome)

Shopify의 CEO가 pi-autoresearch 에이전트에 '더 빠르게 만들어라'는 한 문장 지시를 내려 에이전트가 독자적으로 120회 이상 실험을 수행하며 코드 수정과 테스트를 반복해 템플릿 엔진 성능을 크게 개선하는 사례를 공유했습니다. 자율 코드 최적화 에이전트의 실무적 성공 사례입니다.

https://x.com/GithubAwesome/status/2032651300312146057

#shopify #autonomousagent #aicode #piautoresearch

Github Awesome (@GithubAwesome) on X

Shopify’s CEO just pulled off an absolute masterclass in AI coding! He gave the pi-autoresearch agent one simple instruction for their massive template engine: make it faster. The AI autonomously ran over 120 experiments, rewriting and testing the code. The result? The entire

X (formerly Twitter)
The Daily PerspectiveMar 2

AI and Cybersecurity: Silicon Valley's Promises Are Outpacing the Evidence

#CyberSecurity #ArtificialIntelligence #AICode #AusTech #AusNews #CyberAU

https://thedailyperspective.org/article/2026-03-02-ai-and-cybersecurity-silicon-valleys-promises-are-outpacing-the-evidence-0fb96f4a

AI and Cybersecurity: Silicon Valley's Promises Are Outpacing the Evidence

AI tools are producing vulnerable code faster than security teams can patch it. But should we trust the same vendors to fix what their products broke?

The Daily Perspective
The Daily PerspectiveMar 1

AI Coding Tools Carry Hidden Risks as Claude Flaws Exposed Developer Machines

#CyberSecurity #AICode #Anthropic #ClaudeCode #InfoSec #AusNews

https://thedailyperspective.org/article/2026-03-01-ai-coding-tools-carry-hidden-risks-as-claude-flaws-exposed-developer-machines-24fd408a

AI Coding Tools Carry Hidden Risks as Claude Flaws Exposed Developer Machines

Check Point researchers found three serious vulnerabilities in Anthropic's Claude Code that allowed remote code execution and API credential theft via malicious repositories.

The Daily Perspective
The Daily PerspectiveMar 1

The App That Looked Fine and Wasn't: Vibe Coding's Security Reckoning

#VibeCoding #CyberSecurity #AICode #DataBreach #TechNews #AusNews

https://thedailyperspective.org/article/2026-03-01-the-app-that-looked-fine-and-wasnt-vibe-codings-security-reckoning-f0e9d1f6

The App That Looked Fine and Wasn't: Vibe Coding's Security Reckoning

A researcher found 16 vulnerabilities in one AI-built app on Lovable, exposing 18,000 users including students. Who bears responsibility when AI writes insecure code?

The Daily Perspective
sayzardFeb 21

Anthony Morris ツ (@amorriscode)

Claude의 새로운 데스크톱 앱 업데이트가 공개되어, 개발 환경 통합 기능이 크게 확장되었습니다. 이번 버전에서는 React/DOM 트리에서 직접 컨텍스트를 가져오고, PR을 모니터링하며 자율적으로 문제를 수정하고 코드 변경에 대한 추가 의견까지 제공합니다. 이러한 기능은 개발자 워크플로우 자동화를 강화하며, AI 기반 코드 리뷰와 지속적 통합 환경에 새로운 가능성을 제시합니다.

https://x.com/amorriscode/status/2024942403384377608

#anthropic #claude #developertools #aicode #automation

Anthony Morris ツ (@amorriscode) on X

I'm finding fewer and fewer reasons to leave the desktop app. With today's release Claude can: - Run your dev server and get context from the React/DOM tree - Monitor your PRs and autonomously fix issues - Get a second opinion on your changes Happy Friday, just getting started.

X (formerly Twitter)
Don Curren 🇨🇦🇺🇦Feb 18
“People don’t judge #A.I.code the same way they judge #slop articles or glazed #videos. They’re not looking for the #human #connection of #art. They’re looking to achieve a goal. #Code just has to work.” www.nytimes.com/2026/02/18/o...

Opinion | The A.I. Disruption ...
Opinion | The A.I. Disruption Has Arrived, and It Sure Is Fun

We’re entering a new renaissance of software development. We should all be excited, despite the uncertainties that lie ahead.

The New York Times
Martin Owens Feb 18

Discussions continue in our #AI policy discussion. But I'm reaching my own conclusions on the ethics. Which has always been the main driver of why I contribute to Free Software.

What good is productivity on the backs of bad morals?

https://gitlab.com/inkscape/inkscape-board/-/issues/5

#inkscape #AIPolicy #AICode #llms