16 comments

  • Imustaskforhelp 29 minutes ago
    Please create a way to share conversations. I think that can be really relevant here

    I am not a huge fan of AI but I allow this use case. This is really good in my opinion

    Allowing the ability to share convo's, I hope you can also make those convo's be able to archived in web.archive.org/wayback machine

    So I am thinking it instead of having some random UUID, it can have something like https://duckduckgo.com/?q=hello+test (the query parameter for hello test)

    Maybe its me but archive can show all the links archived by it of a particular domain, so if many people asks queries and archives it, you almost get a database of good queries and answers. Archive features are severely underrated in many cases

    Good luck for your project!

  • wartywhoa23 1 hour ago
    The question is not how to analyze that, it's how to prosecute those who are above the law.
  • andy_ppp 3 hours ago
    I keep thinking that the lack of children’s faces in the blacked out rectangles make the files much less shocking. I wonder if AI could put back fake images to make clearer to people how sick all this is.
    • 13hunteo 18 minutes ago
      I understand the sentiment, but I'm always very concerned when it comes to AI generating pictures of children.
  • yuppiepuppie 1 hour ago
    When first reading OSS, I thought this was going to be an Office of Strategic Services AI [0] agent :)

    [0] https://en.wikipedia.org/wiki/Office_of_Strategic_Services

  • iowemoretohim 6 hours ago
    Those are going to be some spicy hallucinations.
  • wutsthat4 6 hours ago
    And what did you learn?
    • jellyotsiro 6 hours ago
      Trump famously told New York Magazine in 2002: "I've known Jeff for 15 years. Terrific guy. He's a lot of fun to be with. It is even said that he likes beautiful women as much as I do, and many of them are on the younger side."

      Trump and Epstein were social acquaintances in Palm Beach and New York circles during the 1990s-early 2000s. They socialized together at Mar-a-Lago and other venues

      • TowerTall 6 hours ago
        Interesting. It is my impression that almost everyone globally already knew this. What else did you learn?
        • jellyotsiro 6 hours ago
          ill take like 1 hour in the evening to dive deeper, i was never familiar with epstein stuff until i built the agent to simplify things for me.
      • ishtanbul 5 hours ago
        This is one of the most widey quoted phrases by trump on the topic of epstein
    • subzero06 4 hours ago
      In 2024, Trump used Epstein's former private jet for campaign appearances
  • sschueller 3 hours ago
    Is it able to handle a much larger dataset? Only a tiny fraction of data has been release from what is looks like.
  • nubg 5 hours ago
    Does this work with vector embeddings?
  • thecopy 2 hours ago
    Reminder that only 1-2% of the files have been released.
    • Terr_ 41 minutes ago
      Yep: Breaking his campaign promises, in violation of the deadlines imposed by US Federal law, and with unlawful levels of redaction.
  • tehjoker 6 hours ago
    This is a good idea. One thing I never understand about these kinds of projects though: why are the standard questions provided to the user as prompts never cached?
    • jampekka 2 hours ago
      Outputs are usually generated with random sampling, so the same prompt may get different outputs.
    • jellyotsiro 6 hours ago
      oh forgot about it, thanks. just a funny project i build in couple hours so didnt really sweat haha
      • tehjoker 6 hours ago
        This agent is really interesting! Learning a lot. Thanks!
  • dfxm12 5 hours ago
    can search the entire Epstein files

    It's worth noting that only about 1% of the files have been released, according to the DOJ.

    Of the released files, many have redactions.

    • Terr_ 40 minutes ago
      Yep, they failed to meet the deadlines required by law, and it's not just any redactions either, but unlawful redactions.
    • King-Aaron 3 hours ago
      If the Lake Michigan thing is just in the first 1%, then whatever's in the other 99% is going to be absolutely disgusting.
      • Terr_ 39 minutes ago
        I would expect a large portion of the remaining records to be internal emails about memos about the process of building a case around evidence, rather than the root evidence itself.

        Not that that would excuse the administration's unlawful behavior so far, or indicate the unreleased 99% can't have some big bombshells.

      • Tom1380 2 hours ago
        I searched it with the tool but nothing came up about Lake Michigan. What happened?
    • jellyotsiro 5 hours ago
      sorry all publicly available files *
  • huflungdung 13 minutes ago
    [dead]
  • inquirerGeneral 1 hour ago
    [dead]
  • p0w3n3d 2 hours ago
    No need to use Claude Sonnet here. Here's much cheaper solution in Python3:

      import sys
      import random
      import re
      
      print('> ',end='', flush=True)
      input_text = sys.stdin.readline().strip()
      
      text = re.sub(r'[^a-zA-Z ]', '', input_text)
      words = text.split()
      random.shuffle(words)
      
      mixed_words = []
      for word in words:
        n = random.randint(10, 500)
        mixed_words.append(word + ' ' + '' * n)
      
      print(' '.join(mixed_words))
    • dmos62 1 hour ago
      Ah, yes. Post is an LLM-something project: top comment is a general critique of LLMs. Waiting for this to get old. Meanwhile, at least you get points for being funny.
    • sebastiennight 1 hour ago

          > + '' * n
      
      
      This looks like what you'd get from using text-davinci-003 as the model in your AI-assisted IDE
      • flexagoon 1 hour ago
        I think it looks like what you get by writing code and making a typo.