Anyone thinking the performance of GPT-4 may have degraded, it probably didn’t. As we get used to AI systems, our expectations increases(this is true for any new technology that is still finding its ways, remarkable example is uncanny valley in robotics). The key to working with
@jeande_d
-
An Introduction to Statistical Learning Now Available in Python
By
–
Long-awaited…An Introduction to Statistical Learning, one of the classical machine learning books is finally available in Python. Same contents as existing R version but now with commonly used programming language in data world. Get your (free) copy here:
-
GPT-4 Improves Output With Encouragement and Contextual Feedback
By
–
GPT-4 suddenly understands when you tell it “you can do better”. More context is obviously the only hack you need but “you can do better” is a quick feedback that reminds it that it’s capable. Often helpful in open-ended creative generation where you want different variations in
-
Appreciation for Testing Performance Across Multiple Cost Indicators
By
–
Very much appreciate papers that test the performance of their approaches across different cost indicators. @giffmana is among the people that does this remarkably well
-
Cost Indicators: Understanding Their Meaning and Definitions
By
–
Here are what considered as cost indicators and what they mean. https://
arxiv.org/abs/2110.12894 -
Efficiency Misnomer: Beyond Single Cost Indicators in Model Comparison
By
–
"Efficiency Misnomer" is one of those papers that never gets old. It's hard to compare models from the viewpoint of one single cost indicator(either FLOPs, number of parameters, speed(throughput)). A model that has fewer FLOPs or fewer trainable parameters may still be
-
Representation Learning Course Summer School 2023 at Heinrich Heine University
By
–
Representation Learning Course – Summer School 2023, Heinrich Heine University(HHU) This is an excellent course on representation learning. Covers a wide range of topics including: – Visual self-supervised learning methods
– Natural language representation
– Contrastive -
Bookmarking Key Papers on Learning and Vision-Language Models
By
–
@chelseabfinn on learning to learn with gradients. I bookmarked it and hope to read it sometime: https://
ai.stanford.edu/~cbfinn/_files
/dissertation.pdf
… Also @karpathy on connecting images and texts, which was ahead of time given current progress in visual language learning: https://
cs.stanford.edu/people/karpath
y/main.pdf
… -
Comprehensive Survey on Large Language Models Evaluation Methods
By
–
A Survey on Evaluation of Large Language Models A comprehensive survey of evaluation methods for LLMs. Focus on “what, where and how to evaluate”. Also shed light on success and failure cases of LLMs in different tasks, and future challenges. Paper: https://
arxiv.org/abs/2307.03109 -
Code Interpreter Review by Ethan Mollick: Experiments and Analysis
By
–
Here is a nice review about Code Interpreter by @emollick
. Well written and lots of experiments there! https://
oneusefulthing.org/p/what-ai-can-
do-with-a-toolbox-getting
…