2/2 So, the gold standard remains human preference evaluation, which is expensive and difficult to automate and scale. But even human preference evaluation has its flaws. E.g., see The False Promise of Imitating Proprietary LLMs (
https://
arxiv.org/abs/2305.15717).
MACHINE LEARNING
-
Human Preference Evaluation as LLM Gold Standard Despite Its Limitations
By
–
-
Benchmark Overfitting Problem in Machine Learning Research
By
–
The problem is we still don't have any good benchmarks. And the time a benchmark dataset exists is strongly correlated with the rate of overfitting on these benchmarks. Plus, there are also little accidents like this: https://
x.com/Shahules786/st
atus/1695493641610133600?s=20
… 1/2 -
Deploy Deep Learning Networks to Production Quickly
By
–
Quickly deploy trained #DeepLearning networks into production Learn more http://
spr.ly/6010PoRXQ -
AI Protein Folding: Structure Prediction, Not Process Simulation
By
–
AI is not capable of protein folding though, it can only do the final structure prediction. As an analogy, imagine cooking a meal, the AI can tell you how the final picture of the meal will look like based on a list of ingredients, but it can’t say how to make the meal.
-
Google Brain Early Work: Unsupervised Learning and Speech Recognition
By
–
This was a few years into the Google Brain project, so some of my speaking parts describe some of the early Google Brain work on unsupervised learning, scaling of ML training, speech recognition, etc.
-
Leveraging LLM Omniscience for Advanced Planning Strategies
By
–
Avenging Polanyi's Revenge (Exploiting the Approximate Omniscience of LLMs in Planning..) https://
bit.ly/3ON7Zjx #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Cognitive Design vs Natural Selection in Nanosystems Problem-Solving
By
–
– Read Drexler's _Nanosystems_.
– Why would you expect any of those problems to be harder to solve for a cognitively designed system rather than a mutated-selected one? -
Managing User-Generated Content with AI Technology
By
–
How Businesses Can Manage User-Generated Content With AI
#AI #AIio #BigData #ML #NLU #Futureofwork @ahier @guzmand
@DavidBrin @denisegarth @dez_blanchfield @diioannid @DioFavatas @gerald_bader http://
ow.ly/zkle30swTtU -
Focusing on the Future of Artificial Intelligence and Machine Learning
By
–
Focusing on the future of artificial intelligence
#AI #AIio #BigData #ML #NLU #Futureofwork @DeepLearn007 @albertogaruccio @alvinfoo @andi_staub @andy_lucerne @antgrasso @BernardMarr @enricomolinari http://
ow.ly/qaEq30swTtR -
Key Considerations for Competing in the IoT World
By
–
Considerations When You’re Competing In An IoT World
#AI #AIio #BigData #ML #NLU #Futureofwork @oluskayacan @richardkimphd @MariaFariello @johnpearcenews5 @ResurgentAV @rohanmuralee @globaliqx http://
ow.ly/jesS30swTtQ