Anthropic seems to be silently releasing the "code inpainting" feature for Claude AI on the web. There, you can select a part of the code and ask Claude to explain it or Improve it with a new prompt inside the artifact.
CODE
-
COAR: Component Attribution for Targeted Model Edits
By
–
COAR works by estimating the contribution of each component to the model’s final output. These component attributions act as a counterfactual estimator, enabling targeted model edits w/o additional training.
-
ChatLLM: Create Custom AI Bots from Documents in Minutes
By
–
As part of ChatLLM you can have your own AI engineer!
— Abacus.AI (@abacusai) 28 août 2024
It can create a custom bot based on your documents, create a vector store, a deploy it within minutes!
Easily create an end-to-end RAG system! pic.twitter.com/NRA6Duzk7xAs part of ChatLLM you can have your own AI engineer! It can create a custom bot based on your documents, create a vector store, a deploy it within minutes! Easily create an end-to-end RAG system!
-
Comparaison des langages de templates sur Character AI
By
–
Exactly – but on Character AI they have a more advanced template language to define Character's logic. Let's see how will it turn out
-
Live Broadcast: Training and Using CogVideoX-5B Quickly
By
–
Live broadcast with @_akhaliq , about how to train and quickly use CogVideoX-5B. https://
x.com/i/broadcasts/1
MYGNMennLXKw
… -
Building CLIP-like Models for Fashion Image Retrieval Applications
By
–
Learn the essentials to build a CLIP-like model from scratch for a fashion apparel search app with image retrieval.
— Satya Mallick (@LearnOpenCV) 28 août 2024
CLIP was trained on a massive dataset of image-text pairs, which allows it to excel as a zero-shot classification model.
It can take a given text prompt or labels… pic.twitter.com/gWqqkG1Q9lLearn the essentials to build a CLIP-like model from scratch for a fashion apparel search app with image retrieval.
CLIP was trained on a massive dataset of image-text pairs, which allows it to excel as a zero-shot classification model. It can take a given text prompt or labels -
Paper, repo, and LLM-generated story game Everchanging Quest
By
–
Read their paper (currently exploding the upvote counter):
https://
huggingface.co/papers/2408.14
837
… Their repo: https://
gamengen.github.io In a similar vein, play Everchanging Quest, with LLM-generated stories
https://
huggingface.co/spaces/Jofthom
as/Everchanging-Quest
… -
Text2SQL Limitations: Unifying AI and Databases with TAG
By
–
Text2SQL is Not Enough Unifying AI and Databases with TAG discuss: https://
huggingface.co/papers/2408.14
717
… AI systems that serve natural language questions over databases promise to unlock tremendous value. Such systems would allow users to leverage the powerful reasoning and knowledge -
Platypus: Generalized Specialist Model for Reading Text in Images
By
–
Platypus A Generalized Specialist Model for Reading Text in Various Forms discuss: https://
huggingface.co/papers/2408.14
805
… Reading text from images (either natural scenes or documents) has been a long-standing research topic for decades, due to the high technical challenge and wide -
Recommend JuliusAI for interactive Python plotting
By
–
If there’s a Python/R plotting package that does vaguely what you want try @juliusai — basically a fancier ChatGPT code interpreter where you can install arbitrary packages and it reads the docs so you can just ask for stuff. Handy for plots.