Fun weekend hack: https://
awesome-movies.life
Took all 11,768 movies since 1970
Took each movie's Summary+Plot from Wikipedia, embedded it with OpenAI API (ada-002) Wrapped it up into a movie search/recommendation engine site 🙂
it works ~okay hah, have to tune it a bit more.
CODE
-
Weekend Hack: Movie Search Engine Using OpenAI Embeddings
By
–
-
Linear Model Training with Sample Weights for Class Balance
By
–
didn't follow but sounds interesting. "train a linear model with sample weights to class balance"…?
-
Training SVMs on High-Dimensional Embeddings: Performance and Practical Considerations
By
–
yeah 😀 it's not as bad as it sounds, e.g. using the example in the notebook, training an SVM on ~10K 1536D embeddings is ~1 second. Sometimes it's possible to precompute. And sometimes it's just not worth it, all depends on setting / application.
-
Using GPT to Control Character Animations Based on Emotional State
By
–
> download 50 mixamo animations
> give all their names to GPT
> ask it to output one depending on what it is feeling > play anim in Unreal as conversation happens
> holy shit -
Modularity Approach Enables Faster Development and Collaboration
By
–
Thanks for sharing @JimMarous
. Modularity approach enables faster development, better collaboration and increased flexibility. -
SVMs Outperform k-Nearest Neighbor for Embedding Lookups
By
–
Random note on k-Nearest Neighbor lookups on embeddings: in my experience much better results can be obtained by training SVMs instead. Not too widely known. Short example: https://
github.com/karpathy/rando
mfun/blob/master/knn_vs_svm.ipynb
… Works because SVM ranking considers the unique aspects of your query w.r.t. data. -
ControlNet v1.1 Released: Canny, OpenPose Plus 12 Checkpoints
By
–
The amazing @lvminzhang has open-sourced the next version of ControlNet – Canny v1.1
– Open-pose v1.1
– & 12 others new checkpoints You can find theDiffusers' checkpoints here: https://
huggingface.co/models?sort=do
wnloads&search=lllyasvielcontrol_v11
… -
Largest Hybrid ChatGPT Hackathon with $5k Prizes
By
–
We're working with BerriAI to throw the largest hybrid ChatGPT hackathon this weekend! Everyone can participate There's going to be $5k+ in prizes, office hours, late-night virtual lounges, and more
-
LLMO: The Next Wave of SEO for Large Language Models
By
–
This feels like the next wave of SEO. "LLMO"?(
https://
jina.ai/news/seo-is-de
ad-long-live-llmo/
…). It's as much about populating LLMs w/ good content as gaming them. If developers use LLMs to improve their work (and they are), how do you make sure they have the best possible path to using your code, well? -
Autonomous AI Agents: Internet Research While You Sleep
By
–
Imagine an autonomous helper scouring the internet for info or leads while you sleep.
— Replit ⠕ (@Replit) 14 avril 2023
That’s what agents do and we have several developers ready to build one!
Check out @chillzaza_ demo below for an idea of how agents work.https://t.co/CNcdWmLb3NImagine an autonomous helper scouring the internet for info or leads while you sleep. That’s what agents do and we have several developers ready to build one! Check out @chillzaza_ demo below for an idea of how agents work.