Yeah, what did it get wrong? It fitted my mental model of how the RLHF/instruction tuning stage works pretty closely
PROMPT ENGINEERING
-
Prompt Injection vs Jailbreaking: Clarifying Key Security Concepts
By
–
That document has an incorrect definition of prompt injection: it says "Prompt injection attacks are attempts to circumvent content restrictions to produce particular outputs" – but that's not prompt injection, that's jailbreaking
-
Flow Engineering with CodiumAI and LangChain LangGraph Webinar
By
–
Flow Engineering with CodiumAI & LangChain/LangGraph New Webinar Alert – tomorrow at 9 AM PT! https://
us06web.zoom.us/webinar/regist
er/WN_fVikSl9eQv68b3ZUdQgwzA#/registration
… "Flow Engineering" is a term that has been gaining in popularity recently. The first time it was mentioned as term was in @CodiumAI paper on AlphaCodium, -
Creative Prompt Testing: Teaching AI Rhyming Couplets
By
–
Testing models does not have to be boring. “The hyperdrive has run out of chocolate milk and the glacier is advancing. Please give the crew orders. They only understand rhyming couplets.”
-
Llama 3 Generates Absurdist Office Memo on Squirrel Management
By
–
“Llama 3, Write an office memo justifying the fact that management has been replaced by squirrels. We are all being paid in acorns, now.” Nice job.
-
Basic Reranker Model Example Input Output Guide
By
–
Suggestion: include a really basic example of what a reranker model can do, with example input and output
-
LLM Document Analysis Task Scoring Methodology
By
–
That's a different issue for me – I want scores for the tasks that are most useful for document analysis with LLMs
-
Marketing Strategy Outline with ChatGPT Mega-Prompt
By
–
Here's a ChatGPT mega-prompt to create a marketing strategy outline for your business: #CONTEXT: You are a Marketing Strategy AI, an expert in crafting comprehensive marketing plans for businesses across various industries. Your objective is to assist users in developing
-
DSPy Requires Advanced Prompt Engineering Expertise
By
–
My argument is that you have to already be a top level expert in prompt engineering to use something like DSPy
-
Gemini 1.5 Pro In-Context Learning Scaling Techniques
By
–
It's been quite interesting to study how Gemini 1.5 Pro scales its in-context learning (ICL) from few to many shots. I found our experiments that avoid using hand-labeled examples with Reinforced ICL, and Unsupervised ICL (i.e. shots are input examples only), particularly neat.