• 98 Posts
  • 1.57K Comments
Joined 2 years ago
cake
Cake day: June 15th, 2023

help-circle






  • Unless you actually interact with the developer. Such cases are in example when you do a bug report and discuss this. Or in social media. But its not only about the interaction, but the toxicity of the person towards other people and projects. Also if I am interested and using a tool, then I will probably read blog posts, update notes and so on too.

    Even if I don’t interact with someone, I don’t have to support bad behavior. I also don’t have much faith into the project with a human I dislike how the person treats others. If you don’t care and are unaffected by it, its your decision to do what you want and accept.













  • I mean lot of stuff is written in forums and social media, where people hallucinate. Or even in real life if you talk to one. Its normal for a human to pick up something in their life, later talk about it as a fact, regardless of where they learned it (tv, forum, videogame, school). Hallucinations are part of our brain.

    Sometimes being aware of the hallucination issue is still a hallucination. Sometimes we are also aware of the hallucination an Ai makes, because its obvious or we can check it. And also there are Ai chatbots who “talk” and phrase in a more human natural sounding way. Not all of them sound obvious robotic.

    Just for the record, I’m skeptical of Ai technology… not biggest fan. Please don’t fork me. :D


  • To be fair, humans tend to hallucinate too.

    I asked a local Ai chatbot DeepSeek-R1-Distill-Quen-14B:

    Does Ai hallucinate and is it getting worse? Answer in one paragraph.

    Answer:

    AI does exhibit a form of “hallucination” where it generates plausible but incorrect information, particularly when faced with uncertainty or creative prompts beyond its training scope. This phenomenon occurs as AI constructs logical-sounding answers using available data, even if those answers aren’t accurate. While advancements in AI make these hallucinations more convincing and harder to detect due to improved coherence, the issue isn’t worsening in severity but rather evolving in how it presents itself.