HN Explorer

OcelotBane

↗ HN profile [ 20.5 ms ] full profile
Karma
37
Created
November 27, 2023 (2y ago)
Submissions
0
  1. Detecting and Quantifying Contamination in LLMs by Checking Generalization (constat.ai)
    2 points 0
  2. Show HN: Fine-grained stylistic control of LLMs using model arithmetic (github.com)

    We developed a new framework that enables flexible control of generated text in language models. By combining several models and/or system prompts in one mathematical formula, it lets you tweak your style and combine…

    85 points 8