← Latest products

LLM custom instruction to maximise honesty logic, decrease sycophancy

I use the following custom instruction to maximise honest, accurate, factual responses and decrease sycophancy in LLMs that support custom instructions.

Visit news.ycombinator.comexternal site

Reactions (1)

Similar products

by description similarity

  1. HighSNR

    high-snr.com

    Cut length and noise from your LLM context

    Hacker News6 pts

  2. OpenSkills

    news.ycombinator.com

    Stop bloating your LLM context with unused instructions

    Hacker News9 pts

  3. LLM fine-tuning without infra or ML expertise

    tinytune.xyz

    Hacker News5 pts

  4. LLM Aided Transcription Improvement

    github.com

    I recently submitted another project for using LLMs to correct errors and improve formatting of OCRed documents which was well received.

    Hacker News11 pts

  5. I'm tired of my LLM bullshitting. So I fixed it

    news.ycombinator.com

    As a handsome local AI enjoyer™ you’ve probably noticed one of the big flaws with LLMs: It lies.

    Hacker News5 pts