The Pond

SearchSearch

Search

  • About me
  • My research
  • Random post
  • All posts
  • Open source
  • Subscribe

Tag: language models

9 items with this tag.

  • 11/6/2025

    Consistency Training Helps Stop Sycophancy and Jailbreaks

    • activation engineering
    • language models
    • deepmind
    • AI

  • 1/30/2025

    Steering Gemini Using BIDPO Vectors

    • activation engineering
    • language models
    • deepmind
    • AI

  • 1/15/2025

    Gaming TruthfulQA: Simple Heuristics Exposed Dataset Weaknesses

    • language models
    • critique
    • deepmind
    • AI

  • 1/19/2024

    Don’t Use the “Shoggoth” Meme to Portray LLMs

    • language models
    • critique
    • AI

  • 1/2/2024

    Steering Llama-2 with Contrastive Activation Additions

    • activation engineering
    • language models
    • corrigibility
    • mats program
    • AI

  • 5/13/2023

    Steering GPT-2-XL by Adding an Activation Vector

    • activation engineering
    • language models
    • shard theory
    • mats program
    • AI

  • 10/2/2022

    Four Usages of “Loss” In AI

    • language models
    • AI

  • 7/23/2020

    GPT-3 Gems

    • language models
    • AI

  • 7/20/2020

    To What Extent Is GPT-3 Capable of Reasoning?

    • language models
    • AI