Super valuable! Could even export your best chats, feed it into code interpreter, and ask for the prompts that provided best responses/your favorite (most used) prompts Paste it into a notion database, and share across teams to optimize everyone’s workflows!
PROMPT ENGINEERING
-
Nous Research Launches Hermes 2 Llama-2 70B Model
By
–
Nous Research introduced Hermes 2 Llama-2 70B. It's the org's largest model and is trained on over 1M synthetic data entries, also featuring advanced prompt formats for enhanced dialogue interaction.
-
RAG Alternatives: Time-Based Search for Conversation Memory
By
–
It might not be necessary to use RAG for remembering and searching conversations with users. We have 'time' as a precise formatting standard for data, and there's the handy search tool 'Ctrl + F.' Surprisingly, this is an approach from OpenAI.
-
Self-RAG: Self-Reflection for Reliable Retrieval-Augmented Generation
By
–
Self RAG Self-reflection is one of the most interesting ideas in RAG, giving an LLM the ability to self-correct problems in retrieval and / or generation. But, implementing this reliably can be tricky. We've found that graphs are a great way to reliably express logical flows,
-
Managing conversation context and intent in LLMs
By
–
Might be an interesting option. For now it is simpler to start a new chat sometimes than explain to llm that you have a new intent
-
Exploring Creative Possibilities With Image Prompt Generation
By
–
Beautiful! We can tell you really spread your wings with this image prompt
-
Challenges in preventing LLMs from adding hashtags to outputs
By
–
It is quite tricky to teach GPT not to add hashtags if you ask to write for X. You always have to ask to remove them later. Useless
-
Connecting Chatbots to External Data Sources via RAG
By
–
Learn how to connect chatbots to external data sources via RAG: https://
txt.cohere.com/exploring-chat
-rag/
… -
Improving GPT Writing Style and Humanization via Prompting
By
–
What is the best way to improve GPT writing style and prevent it from writing sentences like “In what marks an exciting development in the realm of AI and machine learning…”? To make them more humanized. Asking for a friend
-
Industry’s First Generative AI Learning Pathway and Certification
By
–
Say hello to the industry’s first #GenerativeAI Learning pathway and certification With this new learning offering, you’ll upskill in the fundamentals you need to build and fine-tune LLMs, develop RAG applications, deploy responsible #GenAI, & more https://
bit.ly/47PcOPy