In May I ran my first cohort-based course: How to Build an AI Chatbot. 80 students built their own AI chatbot in 30 days—using ChatGPT to help them code. I was blown away by some of the projects students produced. Here are a few of them:
@danshipper
-
GPT-4 Native Tool Use Makes Building Powerful LLM Agents Easier
By
–
This week @OpenAI gave GPT-4 the ability to use tools natively in their API. This instantly makes it easier to build powerful LLM use cases like agents with far less code than ever before. I dig into what it all means here:
-
Gmail’s New AI Feature Helps Write Emails on iOS Android
By
–
Article: https://
bgr.com/tech/gmails-ne
w-ai-feature-is-ready-to-help-you-write-emails-on-ios-and-android/
… -
Google Launches AI-Powered Help Me Write Feature in Gmail
By
–
Google is rolling out an AI-enabled “Help Me Write” function in Gmail. Am I going to have to start using Gmail again??
-
RLHF Training Method Reduces Human Rater Involvement Requirements
By
–
Yes and afaik the way they use RLHF requires less involvement from human raters, will try to find something
-
Azure AI versions availability versus general cloud API access
By
–
You can get versions that are on Azure but I don’t think the general cloud API is!
-
Anthropic Models Achieve SOC HIPAA Compliance for Regulated Sectors
By
–
Anthropic’s models are now SOC and HIPAA compliant! This is great for anyone trying to build LLM use cases in regulated environments:
-
OpenAI Releases Tool Use for GPT-4 API
By
–
Wow! @OpenAI released tool use as part of the new GPT-4 API. This unblocks a huge barrier to building effective agents https://
openai.com/blog/function-
calling-and-other-api-updates
… -
Chat Completion API compatibility question
By
–
super cool!! does it work with the Chat Completion API?
-
OpenAI’s Rare Success Among Billion-Dollar Startup Failures
By
–
OpenAI might be the only consumer tech product startup that raised > $100m prior to launch, and actually made it work. A graveyard of others have tried and failed (Magic Leap, Juicero, Quibi, etc)