EUNO.NEWS EUNO.NEWS
  • All (21181) +146
  • AI (3169) +10
  • DevOps (940) +5
  • Software (11185) +102
  • IT (5838) +28
  • Education (48)
  • Notice
  • All (21181) +146
    • AI (3169) +10
    • DevOps (940) +5
    • Software (11185) +102
    • IT (5838) +28
    • Education (48)
  • Notice
  • All (21181) +146
  • AI (3169) +10
  • DevOps (940) +5
  • Software (11185) +102
  • IT (5838) +28
  • Education (48)
  • Notice
Sources Tags Search
한국어 English 中文
  • 3 weeks ago · ai

    Why Your AI Needs the Right to Say 'I Don't Know'

    Rethinking Hallucination I used to think hallucinations were a knowledge problem—AI making things up because it didn’t know the answer. After months of working...

    #hallucination #prompt engineering #context gaps #LLM safety #AI assistants #AI accuracy
  • 0 month ago · ai

    On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs

    Article URL: https://arxiv.org/abs/2512.01797 Comments URL: https://news.ycombinator.com/item?id=46354773 Points: 25 Comments: 38...

    #hallucination #LLM #neuron interpretability #language models #arxiv
  • 1 month ago · ai

    Why your AI assistant lies to you (and how to fix it)

    You ask your AI assistant a simple history question about the 184th president of the United States. The model does not hesitate or pause to consider that there...

    #hallucination #AI assistants #LLM reliability #fact‑checking #enterprise AI #mitigation techniques
  • 1 month ago · ai

    Prompt Length vs. Context Window: The Real Limits Behind LLM Performance

    Prompt Length vs. Context Window: Why Size Still Matters Large language models have evolved insanely fast in the last two years. GPT‑5.1, Gemini 3.1 Ultra, Cla...

    #LLM #context window #prompt engineering #token limits #model memory #GPT-5.1 #Gemini 3.1 Ultra #Claude 3.7 Opus #hallucination
EUNO.NEWS
RSS GitHub © 2026