"His business, built entirely with AI assistance and 'zero hand-written code,' was experiencing bypassed subscriptions, maxed-out API keys, and database corruption."

https://nmn.gl/blog/vibe-coding-fantasy

N’s Blog · Mar 20Vibe Coding is a Dangerous FantasyLast week, X exploded when a “vibe coder” announced his SaaS was under attack. His business, built entirely with AI assistance and “zero hand-written code,” was experiencing bypassed subscriptions, maxed-out API keys, and database corruption. His follow-up admission made this notable: “as you know, I’m not technical so this is taking me longer than usual to figure out.” As someone deeply immersed in the AI code generation space, I’ve been watching this unfold with a mix of sympathy and frustration. Let me be clear — I’m not against AI-assisted development. My own tool aims to improve code generation quality. But there’s a growing and dangerous fantasy that technical knowledge is optional in the new AI-powered world. After observing many similar (though less public) security disasters, I’ve come to a controversial conclusion: vibe coding isn’t just inefficient — it’s potentially catastrophic.

#solidstatelife #ai #genai

**Wayne Radinsky** @waynerad@mastodon.social · Feb 15

Feb 15

Wayne Radinsky @waynerad@mastodon.social

New research on AI and code quality. The people who did the study last year showing AI increases "churn" did a follow-up study this year.

AI enables developers to produce new code substantially faster at the cost of long-term maintainability. Code is added about ~20% faster, but "churn" is ~50% higher, code duplication is ~30% higher, and refactorization is ~80% lower.

https://www.youtube.com/watch?v=Et8CqMu_e6s

YouTubeNew Research On CoPilot And Code QualityBy ThePrimeTime

#solidstatelife #ai #genai

**Winbuzzer** @winbuzzer@mastodon.social · Dec 27, 2024

Dec 27, 2024

Winbuzzer @winbuzzer@mastodon.social

Chinese artificial intelligence lab DeepSeek has introduced DeepSeek V3 a open-source AI model that nearly closes the gap to GPT-4o and Claude 3.5 Sonnet. #AI #OpenSource #OpenSourceAI #DeepSeekV3 #DeepSeek #AIResearch #CodingAI #AIModels

https://winbuzzer.com/2024/12/27/deepseek-v3-new-open-ai-model-surpasses-rivals-and-challenges-gpt-4o-xcxwbn/

**Reuben Walker aka mobileatom** @mobileatom@flipboard.com · Oct 29, 2024

Oct 29, 2024

Reuben Walker aka mobileatom @mobileatom@flipboard.com

GitHub’s Copilot goes multi-model and adds support for Anthropic’s Claude and Google’s Gemini. #CodingAI

https://techcrunch.com/2024/10/29/githubs-copilot-goes-multi-model-and-adds-support-for-anthropics-claude-and-googles-gemini/?utm_source=flipboard&utm_medium=activitypub

Posted into Coding is Living @coding-is-living-mobileatom

TechCrunch · Oct 29, 2024GitHub's Copilot goes multi-model and adds support for Anthropic's Claude and Google's Gemini | TechCrunchGitHub today announced that it will now allow developers to switch between a number of large language models when they use Copilot Chat, its code-centric

**Lorenzo 'kelset' Sciandra** @kelset@mastodon.online · Apr 15, 2024 *

Apr 15, 2024 *

Lorenzo 'kelset' Sciandra @kelset@mastodon.online

Here's an #AI** **thought experiment: today** **#codingAI (s) are pretty bad still. In 5 years, they'll be good at what we're trying to get them to do now.

On that trajectory, in 10 they will be able to do a lot more. So here's my question: when AI will be the primary coder, will it develop its own coding language? More performant and better than anything we've ever created so far?

Or will it just converge/loop back to Assembly 'cause that's the root and it's more efficient?