Hacker News new | ask | show | jobs
user: Joschkabraun
created: 2020-04-09
karma: 26

submissions:

Tactics for multi-step LLM app experimentation
1 points | 0 comments
A Systematic Workflow to Build Production-Ready LLM Applications
3 points | 0 comments
Tracking Instructor Validation Errors
1 points | 0 comments
Generate synthetic data for Q&A tasks via instructor in TypeScript
2 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Anthropic's Haiku Beats GPT-4 Turbo in Tool Use
48 points | 14 comments
Ask HN: Who is building on top of OpenAI's Assistants API?
2 points | 0 comments
Observability and Testing of OpenAI's Assistants API
1 points | 0 comments
LLM evals on labeled data
1 points | 0 comments
Building and Evaluating Evals for Retrieval
2 points | 0 comments
Reproducible LLM Experimentation with DVC
1 points | 0 comments
0 points | 0 comments
0 points | 0 comments
First LLM playground to visualize log-probabilities for OpenAI models
1 points | 0 comments
Logprobs in OpenAI API
3 points | 1 comments
Evaluation metrics for any kind of LLM app: RAG, chat, summarization, etc.
1 points | 0 comments
Show HN: Reference-free evaluation of LLM-powered chatbots
2 points | 0 comments
0 points | 0 comments
The first playground to experiment with the GPT-4 Vision API
5 points | 1 comments
0 points | 0 comments
0 points | 0 comments
How has the ChatGPT model changed from March to June?
5 points | 2 comments
How to Personalize Stable Diffusion for All the Things
3 points | 0 comments