Stories by fatso784

EvalGen: Helping Developers Create LLM Evals Aligned to Their Preferences

Semantic Commit: Helping Users Update Intent Specifications for AI Memory

What AI Engineers Can Learn from Qualitative Research Methods

DocETL: A tool for creating LLM-powered data processing pipelines

Aligning LLM-as-a-Judge with Human Preferences

LLM Wrapper Papers Are Hurting HCI Research

Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs

If in a Crowdsourced Data Annotation Pipeline, a GPT-4

Antagonistic AI

How to Compare Prompts with ChainForge [video]

AI for ChainForge Beta

ChatGPT does not have seasonal affective disorder

There is no "seasonal affective disorder" of ChatGPT

There will never be fully automated prompt engineering

ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing

Ask HN: Have LLM API Updates or Deprecations Impacted You?

Apple’s ML model and dataset introspection API

Show HN: ChainForge, a visual tool for prompt engineering and LLM evaluation

Continue multiple conversations simultaneously across multiple LLMs

ChainForge now supports chat evaluation

1