Global AI Weekly
Issue number: 16 | Monday, August 28, 2023
Highlights
}
Custom instructions for ChatGPT
We’re rolling out custom instructions to give you more control over how ChatGPT responds. Set your preferences, and ChatGPT will keep them in mind for all future conversations.
openai.comOpenAI partners with Scale AI to allow companies to fine-tune GPT-3.5
OpenAI, the AI startup behind the viral AI-powered chatbot ChatGPT, plans to partner with third party vendors to make it easier for developers — specifically enterprises — to fine-tune its AI models using custom data. Today, OpenAI announced that it’ll team up with Scale AI, the San Francisco-based data labeling startup, to bring together Scale […]
techcrunch.comVideo
}
Gavita Regunath - Humans In AI
In this video, Gavita, a Principal Data Scientist at Advancing Analytics, shares her journey into the field of AI and machine learning. She discusses how her interest sparked during her master's degree and has since been immersed in the world of AI.
youtube.com
}
Igniting developer innovation with Vector search and Azure OpenAI
In this episode of the AI show, we’ll show how you can combine the capabilities of vectors in Azure Cognitive search with function calling in Azure OpenAI service. Function calling gives the latest versions of gpt-35-turbo and gpt-4 the ability to produce structured JSON outputs based on functions that you describe in the request.
youtube.comArticles
}
How machine learning models can amplify inequities in medical diagnosis and treatment
MIT researchers investigate the causes of health-care disparities among underrepresented groups.
news.mit.eduRun Llama 2 on your own Mac using LLM and Homebrew
Llama 2 is the latest commercially usable openly licensed Large Language Model, released by Meta AI a few weeks ago. I just released a new plugin for my LLM utility that adds support for Llama 2 and many other llama-cpp compatible models.
simonwillison.net
}
Comparing LLMs with MLFlow
Compare LLM inputs, outputs, and generation parameters with mlflow.evaluate()
medium.com
}
Building a ChatGPT-Powered and Voice-Enabled Assistant using React and Express
We will be using the Azure OpenAI Service to access the model, Azure AI Speech to enable speech-to-text and text-to-speech features, an Express server to handle the API requests and communication between the chatbot and the Azure services, and finally a React front-end. The server will receive a call from the main chatbot interface once the user presses the “Send” button and receives the list of previous messages in order to feed these to the model when making the API call.
medium.comUpcoming Events
29 August 2023 - Revolutionize Applications With Vector Search
Online
globalai.community