Live data from Hacker News

Viewing profile — PaulScotti

PaulScotti

HN member
Joined
Sun, Feb 21, 2021, 3:34 PM UTC
HN karma
257
Public activity
18 items

About PaulScotti

https://paulscotti.github.io/

Recent public activity

  1. story
  2. comment
    Comment #40939128

    Thanks for sharing! I read your README and think it's a very interesting research path to consider. I wonder if such an adversarial game approach could be outfitted to not just wel…

  3. comment
    Comment #40936814

    To anyone still finding the game slow due to traffic, you can just git clone the game, add your ANTHROPIC API key to a .env file, and play it locally (this is explained in the READ…

  4. comment
    Comment #40936655

    Thanks! Yes the traffic is making the game slow... To anyone impatient you can just git clone the game, add your ANTHROPIC API key to a .env file, and play it locally. It runs supe…

  5. comment
    Comment #40936607

    Yeah sorry, it is still quite slow due to the traffic. It'd be much faster and robust to run locally via git cloning the repo and adding your own API key as shown in the README For…

  6. comment
    Comment #40936529

    Yeah nice idea -- does sound plausible and would make things much cheaper and faster.

  7. comment
    Comment #40933147

    The Officer doesn't actually get supplied information on the true killer in their context window... so that response you got is actually incorrect. You can check the actual solutio…

  8. comment
    Comment #40930813

    Upgraded the server and should now be working... I think

  9. comment
    Comment #40930806

    Should be working now and way faster! Had to upgrade the server to increased number of workers

  10. comment
    Comment #40930522

    Haha interesting approach!

  11. comment
    Comment #40930081

    Damn that sucks, sorry. For what it's worth I tried playing the game dozens always asking for an overview as my first message and I never encountered such a response , so hopefully…

  12. comment
  13. comment
    Comment #40930012

    Wow really, can you tell me what you said to get them to confess?

  14. comment
    Comment #40921990

    Sharing a little open-source game where you interrogate suspects in an AI murder mystery. As long as it doesn't cost me too much from the Anthropic API I'm happy to host it for fre…

  15. story
  16. comment
    Comment #38674971

    Guys Figure 1 is not real results, it's an illustration of the "goal" of the paper. The real results are in Table 3. And are much worse.

  17. comment
    Comment #34745849

    There's already been preprints released showing fMRI reconstructions that appear to do better than an implicit multi-class classifier [1] [2]. But also, even if the result is an im…

  18. comment
    Comment #34732325

    Exciting stuff, looking forward to seeing how this current AI revolution leads to improvements in the medical research space -- seems very promising