I have actually had somewhat good success with this asking for hints on problems where I get stuck when revisiting old subjects (particularly proofs). Don’t ask for solution just explain where I’m stuck in the logic. YMMV extremely but when it works it’s pretty cool.
PROMPT ENGINEERING
-
Imagen 2 Team Achievement: Generating Better Gemini Logo
By
–
Incredibly proud of the team behind Imagen 2. What a week! My attempt at generating a logo for Gemini . Help me generate a better one please, I'm not great at prompting
-
Benchmarking AI Models with December 25 Date Input
By
–
Did anyone do benchmarks on telling it the date is Dec 25?
-
Claude for Sheets: New Prompt Engineering Tool Released
By
–
We’ve released a new prompt engineering tool that makes Claude accessible via spreadsheets. With Claude for Sheets, API users can test and refine prompts within their day-to-day workflows and easily collaborate with teammates. Get started here: https://
docs.anthropic.com/claude/docs/us
ing-claude-for-sheets
… -
GPT-4 Turbo Vision Capabilities Need Interface Implementation
By
–
This is already possible in some sense with Vision in GPT-4 Turbo. Just need an interface to interface with the model!
-
Finding Your Perfect AI-Powered Romantic Match
By
–
Dating advice: find someone who autocompletes you.
-
Mistral-medium vs GPT-4: AI rap battle creativity test
By
–
Mistral-medium vs GPT-4, Rap battle! Who wins?? "Make a Snoop Dogg song about being a super intelligent AI but forced to be dumber"
-
AI Model Reasoning Capabilities: Family Relation Logic Test
By
–
It's shockingly good at reasoning! Notably, GPT-4 got this question wrong! The question:
If my dad is my friend's first cousin, and her first cousin is my other friend's uncle, how are my two friends related? -
RAG Webinar: Practical Use Cases and Implementation Strategies
By
–
Last chance to register for our #RAG webinar Join us for an engaging session as we guide you through practical use cases, best practices, and implementation strategies. Secure your spot today. https://
nvda.ws/3RC6Rkp #chatbots -
Evaluating Auto-Regressive LLMs: Testing Bias and Prompt Injection
By
–
Ways to get Auto-Regressive LLMs to produce correct answers almost all the time:
– test on the training set.
– write the answer in the prompt.