AINewsnow

Replit Test Shows AI Coding Bots Fail Up To Half Of New Apps

Browser coding site Replit said Replit ViBench 2.0 found AI coding tools could finish only 49% to 65% of app-building tests, so humans still need to check the work. Key Takeaways Replit released ViBench 2.0, a benchmark of 17 products, 241 feature requests and 544 test plans In Replit ViBench 2.0,…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-10-30 00:00 · DEV Community — Machine Learning
    Replit Test Shows AI Coding Bots Fail Up To Half Of New Apps

More stories

  1. Welcome Le Chonk: Mistral Large 4 on Hugging Face — Hugging Face Blog
  2. Meta quietly launches an AI fashion app called Style Sketch — TechCrunch AI
  3. ChatGPT Enterprise at Zendesk: Putting Company Data to Work — OpenAI YouTube
  4. 8 examples of Gemini 4 Argon in action — Google Gemini Blog
  5. You can now generate, preview, and edit documents, PDFs, presentations, spreadsheets, and more directly in Gemini. — Google Gemini Blog
  6. Canada to Take Equity Stake in AI Firm Cohere — Wall Street Journal Technology
  7. How we detect frontier model misalignment — OpenAI News
  8. Accelerating software delivery with agentic QA automation using Amazon Nova Act – Part 3 — AWS Machine Learning Blog

Get the daily brief of stories like this at 6:30 every morning →