home.social

#vibe-coding — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #vibe-coding, aggregated by home.social.

fetched live
  1. A recent ZDNET report shows 80% of developers feel dependent on AI coding tools, driven into a dopamine-adrenaline feedback loop and verification debt.

    While 51% face higher burnout risks, my personal experience differs. I’ve never felt addicted or burned out using AI, with clear boundaries, it remains a practical and useful tool in my workflow.

    Link: zdnet.com/article/80-of-develo

    #AICoding #SoftwareEngineering #DevCommunity #Tech #programming #AI #VibeCoding

  2. I ran my usual quick speed check on muse-glimmer:30b and qwen3.8:27b in Ollama with a quick “what are your capabilities?”

    Output speed:
    * muse-glimmer:30b
    * eval rate: 1.85 tokens/s

    * qwen3.8:27b
    * eval rate: 1.42 tokens/s

    Two observations:
    1. Muse-Glimmer doesn't say anything about its coding abilities, while Qwen devotes a whole paragraph to it.
    2. Qwen's output is very bursty due to its use of Multi-Token Prediction (MTP).

    #AI #LLM #Qwen #LocalLLM #VibeCoding #Programming #Coding