home.social

#keywordmanipulation — Public Fediverse posts

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

fetched live
  1. Chrome Extensions Under Fire: The Keyword Manipulation Scandal

    A recent investigation reveals a troubling trend among Chrome Web Store extensions, where developers exploit a loophole to manipulate search rankings through misleading keywords and descriptions. This...

    news.lavx.hu/article/chrome-ex

    #news #tech #WebSecurity #ChromeExtensions #KeywordManipulation

  2. Chrome Extensions Under Fire: The Keyword Manipulation Scandal

    A recent investigation reveals a troubling trend among Chrome Web Store extensions, where developers exploit a loophole to manipulate search rankings through misleading keywords and descriptions. This...

    news.lavx.hu/article/chrome-ex

    #news #tech #WebSecurity #ChromeExtensions #KeywordManipulation

  3. Chrome Extensions Under Fire: The Keyword Manipulation Scandal

    A recent investigation reveals a troubling trend among Chrome Web Store extensions, where developers exploit a loophole to manipulate search rankings through misleading keywords and descriptions. This...

    news.lavx.hu/article/chrome-ex

    #news #tech #WebSecurity #ChromeExtensions #KeywordManipulation

  4. Chrome Extensions Under Fire: The Keyword Manipulation Scandal

    A recent investigation reveals a troubling trend among Chrome Web Store extensions, where developers exploit a loophole to manipulate search rankings through misleading keywords and descriptions. This...

    news.lavx.hu/article/chrome-ex

    #news #tech #WebSecurity #ChromeExtensions #KeywordManipulation

  5. @baldur

    Idea of the day: #poison the #AI #Hydra! It works.

    #LLMs "...can be #poisoned through their training data—both the data used in the initial training and fine-tuning...[it is possible to do] #KeywordManipulation and degrade output with 👉as few as a hundred toxic entries,👈..."

    B/c: "... Large AI models are bound to be 👉dangerous👈. Their rushed deployment, especially at..."

    softwarecrisis.dev/letters/goo
    #LLM

  6. @baldur

    Idea of the day: #poison the #AI #Hydra! It works.

    #LLMs "...can be #poisoned through their training data—both the data used in the initial training and fine-tuning...[it is possible to do] #KeywordManipulation and degrade output with 👉as few as a hundred toxic entries,👈..."

    B/c: "... Large AI models are bound to be 👉dangerous👈. Their rushed deployment, especially at..."

    softwarecrisis.dev/letters/goo
    #LLM

  7. @baldur

    Idea of the day: #poison the #AI #Hydra! It works.

    #LLMs "...can be #poisoned through their training data—both the data used in the initial training and fine-tuning...[it is possible to do] #KeywordManipulation and degrade output with 👉as few as a hundred toxic entries,👈..."

    B/c: "... Large AI models are bound to be 👉dangerous👈. Their rushed deployment, especially at..."

    softwarecrisis.dev/letters/goo
    #LLM

  8. @baldur

    Idea of the day: #poison the #AI #Hydra! It works.

    #LLMs "...can be #poisoned through their training data—both the data used in the initial training and fine-tuning...[it is possible to do] #KeywordManipulation and degrade output with 👉as few as a hundred toxic entries,👈..."

    B/c: "... Large AI models are bound to be 👉dangerous👈. Their rushed deployment, especially at..."

    softwarecrisis.dev/letters/goo
    #LLM

  9. @baldur

    Idea of the day: #poison the #AI #Hydra! It works.

    #LLMs "...can be #poisoned through their training data—both the data used in the initial training and fine-tuning...[it is possible to do] #KeywordManipulation and degrade output with 👉as few as a hundred toxic entries,👈..."

    B/c: "... Large AI models are bound to be 👉dangerous👈. Their rushed deployment, especially at..."

    softwarecrisis.dev/letters/goo
    #LLM