Chatbots have plenty of gall when it comes to facts. Good article by Karen Weise and Cade Metz. Worth reading.
LLMS
-
ChatLLM by Abacus AI: Custom AI Models for Organization Knowledge
By
–
Get ChatLLM at https://
abacus.ai/chat_llm by @AbacusAI ◉Train it on your org's knowledgebase and get answers to your questions within seconds.
◉Its custom chat #AI models remember your data's context.
◉Create highly accurate human-like responses for very little cost.
—
#ChatGPT -
200,000 Sign Up for ChatGPT Prompt Engineering Course
By
–
Over 200,000 people have signed up for our new short course! ChatGPT prompt engineering for developers, taught with @OpenAI @isafulf
. You can still access it for free here: -
LangChain 101: Build GPT-Powered Applications
By
–
LangChain 101: Build Your Own GPT-Powered Applications LangChain is a Python library that helps you leverage large language models to build custom NLP applications. https://
bit.ly/41HgC35 -
Compositional Soft Prompting Improves Foundation Model Understanding
By
–
Compositional Soft Prompting (CSP) is a clever technique from @stevebach & team at @BrownUniversity that helps improve how well foundation models like CLIP understand and work with combinations of words and images. It teaches models to recognize various combinations of attributes
-
Nvidia releases 2B GPT model trained on 1.1T tokens
By
–
Somehow missed this but Nvidia has a 2B GPT model trained on… 1.1T tokens https://
huggingface.co/nvidia/GPT-2B-
001
… -
GPT-4 vs Claude+: Advanced AI Models for Complex Tasks
By
–
GPT-4 is significantly more advanced in complex problem-solving and creative writing relative to ChatGPT. Claude+ recently got a significant upgrade and some users find it to be the best model available to the world for creative tasks like generating names and language choices.
-
Speaker at Machine Learning Prague Conference on LLM-Driven Games
By
–
I am excited to share that I have been invited to speak at the Machine Learning Prague conference this year. It is a privilege to have the opportunity to discuss my experience in machine learning alongside other knowledgeable experts. My talk will focus on LLM-driven game
-
AI Industry Race: Weekly Model Announcements Growing Token Counts
By
–
twitter these days: announcement: we launched a model trained to 100B tokens!
2nd week announcement: we launch a model trained to 200B tokens
3rd week announcement: we just launch a model at 300B tokens. might as well be twitter-board (not tensorboard). lol. -
Researcher Scooped by Original Paper’s Self-Criticism
By
–
When you think you found a witty rebuttal to a popular paper only to find out that your ideas have been already scooped by the original paper itself. one step ahead bro. Disclaimer: I have not read this fancy "mirage" paper in detail but here's an excerpt from the original