Okay, they simply used an instruction-based training method derived from LLaVA. It's classic and common to leverage previous research methods to keep advancing the field.
PROMPT ENGINEERING
-
New AI Models, Agents, and Platform Features Announced
By
–
– dalle turbo & better
– voice custom
– new os
– custom ui
– autonomous agents & GPTs chain
– local
– 3d
– new auth0
– blah blah -
GPT as Personal Secretary: AI Assistant for Calendar and Daily Life
By
–
Having GPT work with my calendar and work as my personal secretary. Also having it enabled in something like glasses to interact with reality. In sum: a personal secretary, assistant that really makes life easier.
-
Gemini API Integration with LangChain for LLM Development
By
–
Gemini API with LangChain @arslanchaos put together an AWESOME notebook showing how to use the Google Gemini API with LangChain. Covers: Text Generation
Image Understanding
Safety Features
Streaming and batch support Check it out here: https://
github.com/ArslanKAS/Lang
Chain-for-LLM-App-Development/blob/master/GeminiPro_with_LangChain.ipynb
… -
Midjourney v6 Finally Achieves Winter Scene Rendering
By
–
A winter scene I’ve been prompting since the early days, at last MJ v6 makes it so.
-
ChatGPT Tips: Long Threads vs New Chat Sessions
By
–
Your ChatGPT tip of the day (long threads vs new chats): pic.twitter.com/t20WgpI3Eu
— Logan Kilpatrick (@OfficialLoganK) 22 décembre 2023Your ChatGPT tip of the day (long threads vs new chats):
-
RAG and LLMs Course Finale: LangChain vs LlamaIndex vs OpenAI
By
–
Good morning fellow AI enthusiast! This week's iteration focuses on the last video of our 3-course series on RAG and LLMs with @towards_AI and @activeloop
! https://
open.substack.com/pub/louisbouch
ard/p/langchain-vs-llamaindex-vs-openai?r=25qlky&utm_campaign=post&utm_medium=web&showWelcome=true
… -
AI-Generated Hyperrealistic Pope Portrait Showcases Advanced Image Synthesis
By
–
This was the prompt: “Pope Francis wearing a Balenciaga puffer jacket , taken using a Canon EOS R camera with a 50mm f/1.8 lens, f/2.2 aperture, shutter speed 1/200s, ISO 100 and natural light, Full Body, Hyper Realistic Photography, Cinematic, Cinema, Hyperdetail, UHD, Color
-
Adding More Details to Prompts Improves Results
By
–
You probably just need to add more details to the prompt! From what I can see so far, this version is much more opinionated about details.
-
LangChain vs LlamaIndex vs OpenAI GPTs Comparison Guide
By
–
New video! @langchain vs. @llama_index vs. @OpenAI GPTs: Which one should you use? https://
youtu.be/g84uWgVXVYg