s
Aug. 30, 2023, 2:37 p.m. |

Simon Willison's Weblog simonwillison.net

Llama 2 is about as factually accurate as GPT-4 for summaries and is 30X cheaper


Anyscale offer (cheap, fast) API access to Llama 2, so they're not an unbiased source of information - but I really hope their claim here that Llama 2 70B provides almost equivalent summarization quality to GPT-4 holds up. Summarization is one of my favourite applications of LLMs, partly because it's key to being able to implement Retrieval Augmented Generation against your own documents - where …

ai anyscale api claim generativeai gpt gpt-4 gpt4 information llama llama 2 llms unbiased

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Sr. Software Development Manager, AWS Neuron Machine Learning Distributed Training

@ Amazon.com | Cupertino, California, USA