LLMS - AI Dynamics

Language Models as Realistic Tabular Data Generators

By

–

07 November 2022 5h28

Language Models are Realistic Tabular Data Generators Borisov et al.: https://
arxiv.org/abs/2210.06280 #ArtificialIntelligence #DeepLearning #MachineLearning

→ View original post on X — @montreal_ai

7 November 2022

365-Day Lookback Window Mixed Media Model Strategy

By

@herrmanndigital

–

07 November 2022 0h26

Sir, you need a 365 / 365 look back window and switch to a mixed media model to make it work

→ View original post on X — @herrmanndigital

7 November 2022

Prompt Engineering for AI Agents: Step-by-Step Operation Sequencing

By

@goodside

–

06 November 2022 21h18

The game is “least to most” — have it write out the most mechanical, reliably performed operations first. Then gradually move up to more interpretive and analytical steps, so it’s never asked to do anything multi-step in its head. The prompt should feel like an income tax form.

→ View original post on X — @goodside

6 November 2022

GPT-3 Tokenization Challenges and Model Limitations

By

@goodside

–

06 November 2022 20h38

+1 for this approach. GPT-3’s tokenization is a big gotcha. Model doesn’t see text as sequences of characters unless you add spacing/hyphens. It can’t even reliably tell you the last letter of a word without first rewriting it that way. Similar for counting length:

→ View original post on X — @goodside

6 November 2022

Large Language Models Demonstrate Self-Improvement Capabilities

By

@montreal_ai

–

06 November 2022 14h34

Large Language Models Can Self-Improve Huang et al.: https://
arxiv.org/abs/2210.11610 #ArtificialIntelligence #DeepLearning #MachineLearning

→ View original post on X — @montreal_ai

6 November 2022

K-Shot Learning for Non-RLHF Tuned LLMs

By

@goodside

–

05 November 2022 21h13

I’ve never seen it work on anything other than RLHF-tuned GPT-3. I’ve wondered if you could k-shot a non-RLHF model with meta-examples of instruction templates followed by input/output pairs for each, but haven’t tried it.

→ View original post on X — @goodside

5 November 2022

100+ Free Data Science and Machine Learning eBooks

By

@marcusborba

–

05 November 2022 17h14

Free eBooks: 100+ Free Data Science Books http://
bit.ly/3AAD4At #NeuralNetworks #MachineLearning #TensorFlow #100DaysOfCode #BigData #Analytics #DevCommunity #Programming #IoT #javascript #Linux #Cloud #Serverless #womenwhocode #Python #RStats #DeepLearning #AI #DataScience

→ View original post on X — @marcusborba

5 November 2022

Cohere Python SDK: Add NLP Features to Your App

By

@cohere

–

05 November 2022 1h21

Add powerful NLP functionality into your app, like sentiment analysis and text summarization, with Cohere's Python SDK. In this tutorial, we show you how – https://
hubs.li/Q01ryKFW0

→ View original post on X — @cohere

5 November 2022