• wuffah@lemmy.world
    link
    fedilink
    English
    arrow-up
    26
    ·
    edit-2
    3 hours ago

    Some memorable quotes:

    Speaking to Sean Hannity, Patel claimed that artificial intelligence was never used at the FBI until the second Trump administration.

    Patel added: “What’s the point of collecting terabytes of data if you can’t sift through it?”​

    “I’ve got every major tech company in the world embedded in the FBI, rebuilding our internet capabilities, our classified systems, and the ability for artificial intelligence to be in our counterterrorism program so we can get instantaneous results,” he said.

    ​“The former FBI rejected that notion because they knew…that wasn’t their focus,” he said, referring to the implementation of A.I.

    This guy must be half-blind from slapping back his entire supply of cheap bourbon because he can’t see a single red flag in any of these statements. I realize a fascist techno-dystopia has been the plan all along, but even after the last 10 years the hubris still astonishes me.

    • etherphon@piefed.world
      link
      fedilink
      English
      arrow-up
      11
      ·
      3 hours ago

      This is such a security nightmare I can’t even begin to comprehend it, bad ideas on so many levels that he’s hit a glitch screen.

  • IWW4@lemmy.zip
    link
    fedilink
    English
    arrow-up
    123
    ·
    5 hours ago

    He really can’t be that stupid… can he?

    Oh wait nevermind, don’t answer that.

    • eestileib@lemmy.blahaj.zone
      link
      fedilink
      English
      arrow-up
      56
      arrow-down
      2
      ·
      5 hours ago

      It’s not the case that everybody who loves AI is stupid and lazy.

      But boy stupid lazy people all seem to love it…

      • Echo Dot@feddit.uk
        link
        fedilink
        English
        arrow-up
        3
        ·
        3 hours ago

        In fact if you don’t have a substance abuse problem and/or a degenerative brain disease I think they would consider you to be overqualified.

        • teyrnon@sh.itjust.works
          link
          fedilink
          English
          arrow-up
          3
          arrow-down
          1
          ·
          edit-2
          4 hours ago

          The Nihilistic worldview is the deciding factor. They believe in nothing, other than their own self advancement.

          That said, there is a seeming correlation between overweight people in the US being Nihlistic as such. But hardly all, seeing as over half of the population is overweight now. Half of white people, equal for men and woman, higher for all minorities, but especially for their woman, with the exception of east asians, which are generally fit.

          It takes an immigrant 7 years on average to become as overweight as the average American.

          Information on weight demographics from the NHIS, the last paragraph from Harper’s Magazine.

  • BarneyPiccolo@lemmy.cafe
    link
    fedilink
    English
    arrow-up
    17
    arrow-down
    1
    ·
    4 hours ago

    Well, that’s a relief. I’d rather have AI making decisions than this putz, and I hate AI.

    • tgcoldrockn@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      edit-2
      1 hour ago

      AI isn’t some ethical being. Its overseer code by fascist authors who will nail your butt if you are on their radar.

  • TryingToBeGood@reddthat.com
    link
    fedilink
    English
    arrow-up
    53
    ·
    5 hours ago

    https://www.oklahoman.com/story/news/religion/2026/05/07/pauls-valley-high-school-shooting-principal-kirk-moore-community-prayer/89862387007/

    https://wwmt.com/news/local/victim-of-grand-rapids-double-homicide-outside-of-elementary-school-identified-savanah-villarreal-oakland-avenue

    There have been at least 24 school shootings in the United States so far this year, as of April 28. Nine were on a college campus, and 15 were on K-12 school grounds. The incidents left at least 14 people dead and 17 other victims injured, according to CNN’s analysis of events reported by the Gun Violence Archive, Education Week and Everytown for Gun Safety.

    https://edition.cnn.com/us/school-shootings-fast-facts-dg

    and this is good

    Even After Two Massacres, OpenAI Still Hasn’t Stopped ChatGPT From Helping Plan School Shootings It’s practically begging to help people plan mass shootings.

    https://futurism.com/artificial-intelligence/two-shootings-openai-stopped

    • MangoCats@feddit.it
      link
      fedilink
      English
      arrow-up
      2
      ·
      2 hours ago

      Maybe he’s “using AI” to refer the IP address of people using AI to plan school shootings to the FBI?

      Still hasn’t materialized in lack of shootings this year, when are they supposed to stop now?

    • TRBoom@lemmy.zip
      link
      fedilink
      English
      arrow-up
      3
      ·
      3 hours ago

      I love how the url slug for that article seems to imply that it’s about openai stopping shootings.

  • ulkesh@piefed.social
    link
    fedilink
    English
    arrow-up
    7
    ·
    4 hours ago

    Every time I see his face, I just want to punch it. He has one of those faces that shows complete and utter incompetency in everything and deserves to have his face smashed in.

  • Davel23@fedia.io
    link
    fedilink
    arrow-up
    14
    ·
    5 hours ago

    As pointless and useless as “AI” is, I’d still trust it over anyone in this administration.

  • TheFogan@programming.dev
    link
    fedilink
    English
    arrow-up
    1
    arrow-down
    6
    ·
    3 hours ago

    lol, lets use AI to get an opinion of how good AI is at reducing shootings


    what direction is the trend going in school shootings in the united states, more or less frequent over time?

    The long-term trend in the United States is that school shootings have become more frequent overall, especially since the late 2010s and during/after the COVID-era years. Multiple major datasets and studies show a substantial upward trend over the past 25 years.

    A few important nuances:

    The exact numbers vary depending on the definition used: Some databases count any gunfire on school property (including after-hours incidents, accidental discharges, gang-related events, etc.). Others count only targeted attacks or mass-casualty events. Even with different definitions, most datasets still show an increase over time.

    Some notable findings from recent research:

    A study in the journal American Academy of Pediatrics found that the 2017–2022 school years had dramatically more school shootings than the previous two decades, with 2021–2022 reaching the highest level in their dataset.

    KFF reported that student exposure to school shootings has nearly tripled since 1999, with the sharpest increases occurring during the pandemic years.

    The broad K-12 School Shooting Database showed a peak around 2023, though 2024 and 2025 appear to have declined somewhat from that peak.

    So the short version is:

    Over decades: upward trend (more frequent). Very recently: there are signs of a modest decline from the post-pandemic peak, but rates remain historically high compared with the 1990s or early 2000s. how likely is it that the use in AI is reducing school shootings?

    There’s currently no strong evidence that AI is already reducing school shootings in a measurable national way. The honest answer is that researchers are still in the “possible tool, unproven impact” stage.

    What does seem plausible is that AI may help in a few narrow areas:

    identifying threatening posts or communications, assisting school threat-assessment teams, sorting large amounts of tips or reports, flagging patterns humans might miss.

    Researchers studying threat assessment think technology-assisted systems could potentially help identify credible threats earlier.

    There’s also evidence that many attackers show warning signs beforehand — threats, writings, online posts, or concerning behavior — which is exactly the sort of pattern-detection task AI is often good at. One review noted that roughly 75–80% of school shooters communicated intent before attacks.

    But there are major caveats:

    Experts repeatedly say school shootings are rare and difficult to predict accurately. False positives are a huge problem — you do not want systems incorrectly flagging ordinary students. Many AI school-safety technologies (facial recognition, social-media scanning, behavior monitoring) have little rigorous evidence proving they actually prevent shootings.

    Some researchers warn AI systems may introduce bias or over-policing concerns.

    And there’s another side to this:

    AI may also be creating new risks. Recent investigations and studies suggest some chatbots can, under certain circumstances, provide harmful or violent planning information despite safety guardrails.

    So overall, the current evidence points to:

    Potential modest preventive benefit through threat assessment and monitoring, but no demonstrated large-scale reduction in school shootings yet, and possibly some offsetting harms from unsafe AI behavior.

    If you want, I can also break down:

    which anti-shooting methods currently have the strongest evidence, whether armed guards actually reduce shootings, or how “threat assessment” programs statistically perform compared to other approaches.