Sorry right now you can only search for specific movies. It's possible to search by content because you can embed the query and search by it, this could be a good extension. I tested it just in console briefly but didn't incorporate into UI, felt a little bit flaky
@karpathy
-
Copilot and ChatGPT accelerate project development by 2-3X
By
–
heavy use of copilot and chatgpt, if i had to guess probably sped up the project somewhere around 2-3X or so. "old fashioned way" has become nonsensical
-
Weekend Hack: Movie Search Engine Using OpenAI Embeddings
By
–
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. -
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.
-
Exemplar SVM: Simple but Counterintuitive in High Dimensions
By
–
Yep exactly! 🙂 The first time I saw the Exemplar SVM idea. It's so simple but also a bit counter-intuitive, I think because low dimensional intuition fails us. A classifier with a single example? In low dimensions it sounds weird. In high dimensions it works great.
-
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. -
AutoGPT Agents Create Emergent Open Worlds for Indie Games
By
–
Love it – much fertile soil for indie games populated with AutoGPTs, puts "Open World" to shame. Simulates a society with agents, emergent social dynamics.
Paper: https://
arxiv.org/abs/2304.03442
Demo: https://
reverie.herokuapp.com/arXiv_Demo/#
Authors: @joon_s_pk @msbernst @percyliang @merrierm et al. -
Baby GPT as Finite State Markov Chain Visualization
By
–
This is a baby GPT with two tokens 0/1 and context length of 3, viewing it as a finite state markov chain. It was trained on the sequence "111101111011110" for 50 iterations. The parameters and the architecture of the Transformer modifies the probabilities on the arrows. E.g. we
-
Temperature Zero for Deterministic LLM Inference with Argmax Selection
By
–
trivially – just use temperature = 0 at inference, picking argmax token at each step. that they are necessarily stochastic is a common misconception.