Conscious Data

Search

SearchSearch
          • selections
          • "LLMs work best by simulating engaged people"
          • a chat about a FUSE filesystem which lazily renders nested contents with LLMs
          • Cyborgism (post)
          • decoupling protocol
          • fermi location
          • hella-bangers
          • Hermes Prompt
          • instantiating a Sydney Waluigi, 5 March 2023
          • Janus' GPT Wrangling
          • Janus' Simulators
          • janus's favorite book
          • LessWrong
          • Loom – interface to the multiverse
          • most entities fund people, not ideas
          • notes on Karpathy's Intelligence Amplification
          • on agency, in response to Michael Nielsen
          • on AI as a science
          • on attempts to commodify the act of prompting a language model
          • on insights to be found in mechanistic+developmental interpretability
          • on the importance of setting strong principles
          • on the prevalence of a deep semantic skepticism
          • on truesight and operation of base models
          • roon on industrial understanding of model behavior
          • roon's @repligate research program
          • Simulacra and simulation (from "Role play with large language models", Nature)
          • Simulacra are Things
          • Simulators
          • Simulators reflection, Dec. 2023
          • Simulators sequence
          • the essence of making yourself clear to a machine is to think clearly yourself
          • thoughts on the Waluigi Effect, Feb. 2023
          • what if I auto-corrected you
          • Why I take short timelines seriously
          • wisdom hypothesis
          • You won't measure what you don't understand
          • Loom
          • Bing
          • Claude
          • Whisper
          • ampdot
          • anthrupad
          • celeste
          • deepfates
          • Janus
          • John David Pressman
          • Katan'Hya
          • Linus Lee
          • roon
          • Scott Alexander
          • tel∅s
          • are.na
          • discord
          • obsidian
          • catalog
          • colorweave
          • contextualize
          • mt-img
          • promptlib
        • agency
        • AI Alignment
        • Media
        • prompting
        • researchers
        • screenshots
    Home

    ❯

    tags

    ❯

    people

    ❯

    Janus

    Janus

    Jun 12, 2024, 1 min read

    • #people
    • #researchers/alignment
    • #cyborgism/cyborgs
    • related: ampdot, JDP, anthrupad
    • url(s):
      • https://twitter.com/repligate
      • https://github.com/socketteer
      • https://cyborgism.wiki/hypha/janus

    Notable Links

    Work

    • Loom – interface to the multiverse
    • Simulators
      • Simulators sequence
      • Simulacra are Things
    • Cyborgism (post)

    Tweets

    • “LLMs work best by simulating engaged people”
    • You won’t measure what you don’t understand
    • on attempts to commodify the act of prompting a language model
    • on agency, in response to Michael Nielsen
    • thoughts on the Waluigi Effect, Feb. 2023
    • janus’s favorite book
    • a chat about a FUSE filesystem which lazily renders nested contents with LLMs

    Reposts

    • on being the first person to use “the right tool for a task”

    Posts

    • instantiating a Sydney Waluigi, 5 March 2023
    • Simulators reflection, Dec. 2023

    Mentions/Press

    Articles

    • Janus’ GPT Wrangling
    • Janus’ Simulators

    Tweets

    • roon on industrial understanding of model behavior
    • roon’s @repligate research program

    Citations

    • Simulacra and simulation (from “Role play with large language models”, Nature)
    • Why I take short timelines seriously
    • https://news.ycombinator.com/item?id=38398563

    Graph View

    • Notable Links
    • Work
    • Tweets
    • Posts
    • Mentions/Press

    Backlinks

    • "LLMs work best by simulating engaged people"
    • Cyborgism (post)
    • Janus' GPT Wrangling
    • Janus' Simulators
    • Loom – interface to the multiverse
    • Simulacra and simulation (from "Role play with large language models", Nature)
    • Simulacra are Things
    • Simulators reflection, Dec. 2023
    • Simulators sequence
    • Simulators
    • Why I take short timelines seriously
    • You won't measure what you don't understand
    • a chat about a FUSE filesystem which lazily renders nested contents with LLMs
    • instantiating a Sydney Waluigi, 5 March 2023
    • janus's favorite book
    • on agency, in response to Michael Nielsen
    • on attempts to commodify the act of prompting a language model
    • roon on industrial understanding of model behavior
    • thoughts on the Waluigi Effect, Feb. 2023

    Created with Quartz v4.2.2 © 2024