The hottest Human feedback Substack posts right now

And their main takeaways
Category
Top Technology Topics

Hybrid Evaluation: Scaling human feedback with custom evaluation models

LLMs for Engineers • 159 implied HN points • 15 Nov 23
🕹 Technology AI Machine Learning Human feedback Automation
  1. Human feedback is still very important for evaluating models, especially in areas like customer support, but it can slow things down and increase costs.
  2. Combining human input with automated, model-based evaluation can help improve efficiency and accuracy, reducing errors significantly.
  3. Using fewer human-labeled examples with smart bootstrapping techniques can still yield good results, making it cheaper and faster to train evaluation models.

It was the best of RLHF, it was the worst of RLHF

Gradient Ascendant • 11 implied HN points • 30 Oct 23
🕹 Technology Artificial Intelligence Machine Learning Human feedback Information processing Data Training
  1. RLHF, or Reinforcement Learning from Human Feedback, is essential for ensuring AI models generate outputs that align with human values and preferences.
  2. RLHF can lead to outputs that are more homogenized, less insightful, and use weaker language, which may limit diversity and creativity.
  3. There is growing discussion in the AI community about making RLHF optional, especially for smaller models, to balance the costs and benefits of its implementation.

Putting the human touch on LLMs

Molly Welch's Newsletter • 1 HN point • 30 Mar 23
🕹 Technology AI Human feedback Machine Learning Language Models Ethics
  1. Using human feedback to refine large language models is key for aligning them with user values and preferences.
  2. Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for enhancing the quality of LLM outputs.
  3. Incorporating human touch into LLMs raises questions about scalability, cost, decision-making regarding whose feedback matters, and potential policy implications.

Constitutional AI, Law and Freedom

Autonomy • 1 HN point • 30 Jan 24
🕹 Technology AI Ethics Philosophy Training Human feedback
  1. Claude, an AI chatbot was trained with 'Constitutional AI' principles based on UN's human rights and Apple's terms of service.
  2. The term 'Constitutional AI' is problematic because principles are applied only during training, not during actual AI responses.
  3. The concept of free will is complex and AI self-consciousness raises questions about autonomy and responsibility in decision-making.
Get a weekly roundup of the best Substack posts, by hacker news affinity: