LLMS - AI Dynamics

LLaMa Chat Interface Testing and Parameter Switching Updates

By

–

19 July 2023 5h35

Thanks for pressure testing LLaMa Chat! We're investigating the interface issue. As for parameter switching, we're exploring possibilities for future updates. Stay tuned and thanks for helping us improve!

→ View original post on X — @perplexity_ai

19 July 2023

Meta Launches LLaMa Chat: Fast LLM Inference Platform

By

@perplexity_ai

–

19 July 2023 4h29

Introducing LLaMa Chat: The fastest way to chat with @MetaAI
/
@meta
's Llama2! Try it here: https://
llama.perplexity.ai, feedback appreciated! This is our first step towards building a blazing-fast LLM inference completely in-house, for everyone to try. What's next? We'll be

→ View original post on X — @perplexity_ai

19 July 2023

Circuit Analysis Interpretability Scaling in Chinchilla Language Models

By

@_akhaliq

–

19 July 2023 4h17

Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla paper page: https://
huggingface.co/papers/2307.09
458
… Circuit analysis is a promising technique for understanding the internal mechanisms of language models. However, existing analyses are done

→ View original post on X — @_akhaliq

19 July 2023

Llama 2 Paper Page Now Available on Hugging Face

By

@_akhaliq

–

19 July 2023 4h06

paper page for llama 2 is up: https://
huggingface.co/papers/2307.09
288
…

→ View original post on X — @_akhaliq

19 July 2023

ChatGPT’s Behavior Changes Over Time: March to June 2023

By

@_akhaliq

–

19 July 2023 3h48

How is ChatGPT's behavior changing over time? paper page: https://
huggingface.co/papers/2307.09
009
… GPT-3.5 and GPT-4 are the two most widely used large language model (LLM) services. However, when and how these models are updated over time is opaque. Here, we evaluate the March 2023 and June

→ View original post on X — @_akhaliq

19 July 2023

Orca: Progressive Learning from GPT-4 Explanation Traces

By

@nathanbenaich

–

19 July 2023 0h57

https://
microsoft.com/en-us/research
/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/
…

→ View original post on X — @nathanbenaich

19 July 2023

Step-by-Step Reasoning Improves AI Learning Like Human Cognition

By

@nathanbenaich

–

19 July 2023 0h57

Eerie and logical that step-by-step reasoning is a better way to teach AI systems given that’s how we humans learn complex tasks. “Our research indicates that learning from step-by-step explanations, whether these are generated by humans or more advanced AI models, is a

→ View original post on X — @nathanbenaich

19 July 2023