Before we start, this is Level 0. A library of functions built by human developers that the AI has access to. The agent is not building its own functions.* *tools, skills, api calls, are all just functions
PROMPT ENGINEERING
-
Three Levels of Self-Building Autonomous Agents
By
–
A helpful autonomous agent has access to all the tools you need – and nothing more. But we all have different needs, changing all the time, so… what we need is a self-building autonomous agent. Here, I'll describe the 3 levels of self-building autonomous agents:
-
CaptainCaption: GPT-4-Vision Based Image Captioning Tool
By
–
CaptainCaption GPT-4-Vision Based Image Caption Generator github: https://
github.com/42lux/CaptainC
aption
… A gradio based image captioning tool that uses the GPT-4-Vision API to generate detailed descriptions of images. Features Prompt Engineering: Customize the prompt for image description -
Fine-tuning and Model Merging: Practical Tips and Tricks
By
–
Here's my @aiDotEngineer talk in SF about fine-tuning and model merging It's a quick overview of the field with practical tips and tricks to make the best merges and finetunes. Hope you'll like it! 🙂
-
Multimodal AI Model Handles Text and Coding Tasks
By
–
Yup that's what I mean. I tried doing some text-only chat on the playground but it looks like it actually requires an image input. So I put in a random pic and asked it coding questions, and it seemed to do ok.
-
Teaching Prompt Engineering in Schools: Industry Experts Podcast
By
–
we should teach prompt engineering in schools
— Latent.Space (@latentspacepod) 25 septembre 2024
any guesses for title of our next pod with @ShunyuYao12 and @hwchase17? pic.twitter.com/qTriYLYRXJwe should teach prompt engineering in schools any guesses for title of our next pod with @ShunyuYao12 and @hwchase17
? -
Comparing prompt effectiveness across LLMs
By
–
Only text preview. My most important prompt gives exactly the same response as Llama 3
-
Compound AI Systems Design: Scaffolding for Observe-Execute-Reflect
By
–
+1 system design for compound AI systems. matches our findings — once you figure out how to design the scaffolding around the AI for it to observe, execute, reflect, you can get impressive results from it.
-
LLM Validators Alignment Human Preferences Evaluation
By
–
Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences Tune in to the Paper Club today to cover Shreya's latest hit with @eugeneyan
! link below -
Autocompletion Model and Markdown Compatibility Questions
By
–
Do you know the model they use for autocompletion? Also, does it work with markdown?