It is a surprise that you can move very complex prompts (like pages of text) from Claude 3 to GPT-4 to Gemini 1.5 and have it generally work quite well without modification. Tweaking is usually only a couple of minutes to match the models "mood." I wouldn't have expected that.
PROMPT ENGINEERING
-
Multi-AI Model Interaction Unlocks Powerful Conversational Capabilities
By
–
The ability to interact with multiple AI models in one conversation unlocks powerful new ways to engage with AI. You can ask Claude 3 Opus to explain a topic to you, compare the outputs from GPT-4 and Gemini 1.5 Pro, then add Web Search bot for the latest information. (2/4)
-
Model Fine-Tuning for Human Preferences
By
–
Your model, after some fine-tuning for human preferences.pic.twitter.com/lzq5WAqP1b
— hardmaru (@hardmaru) 15 avril 2024Your model, after some fine-tuning for human preferences.
-
LLM Generative Capacity and Idea Diversity with Right Prompts
By
–
I think we need to balance this intuition with the fact that LLMs can also be highly generative & even novel. Our paper shows that, with the right prompts, idea diversity from LLMs is high: https://
papers.ssrn.com/sol3/papers.cf
m?abstract_id=4708466
… Or from an esoteric perspective, take: https://
dreams-of-an-electric-mind.webflow.io -
Flow Engineering with CodiumAI and LangGraph Webinar
By
–
Flow Engineering with CodiumAI & LangChain/LangGraph New Webinar Alert: 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, where they used flow -
Can LLMs perform tasks without external tools?
By
–
Is this something we would expect an LLM to do without tools?
-
AI Models Can Use Links in Prompts for Context
By
–
If the context is online, you can actually paste links to it in the prompt, and the model can decide to use it if it wants! So it’s very likely possible.
-
Planning Pattern: How LLMs Drive Autonomous Agent Decision-Making
By
–
Planning is a key agentic AI design pattern in which we use a large language model (LLM) to autonomously decide on what sequence of steps to execute to accomplish a larger task. For example, if we ask an agent to do online research on a given topic, we might use an LLM to break
-
GPT-4 Predicts Future Events Accurately Through Narrative Storytelling
By
–
Not 100% sure what to make of this timey-wimey paper showing GPT-4 is able to predict the future quite accurately (or, after least make guesses about events that happen after its training cut-off) but only when asked to tell stories about what will happen. https://
arxiv.org/abs/2404.07396 -
DSPy: Automatic Prompt Optimization Through Example Derivation
By
–
My current mental model of DSPy is that it leans into the thing where LLMs can produce much better output if you prime them with the right examples – then helps automatically derive the best examples based on running some evals I may have misunderstood it though