How do you generate these beautiful pictures so fast? He posted this only 16 minutes before!
INNOVATION
-
Koala and Vicuna: UC Berkeley’s Concurrent LLM Efforts
By
–
Koala and Vicuna are friends, and concurrent efforts within UC Berkeley! You can try out both models at http://
chat.lmsys.org -
Collaborative Learning Beats Solo Work in AI Communities
By
–
For me, it’s more fun to collaborate and learn with others vs doing it alone
-
Adapting Prompts for Specific Use Cases Increases AI Power
By
–
Nice, that’s a great use case! I bet adapting prompt to specific use case make this much more powerful.
-
New /describe Command Transforms Images into Words
By
–
Today we're releasing a /describe command that lets you transform images-into-words. Give it a shot! We think this tool will transform your liguistic-visual process both in terms of creative power and discovery.
-
GPT-4 Replit Integration Automates Code Fixing
By
–
@Replit and @openai #GPT4 combine to make it insanely easy for morons like me to play with code. See here how http://
wolverine.py by @biobootloader uses GPT4 to fix code right in the repl. You can actually see your code getting fixed…amazing. https://
loom.com/share/6dbf0e74
97f24c7789583dc52c67d556
… -
Hybrid Search Strategy for LLM Date Filtering and Vector Queries
By
–
So I think this is a case where you might to use hybrid search. You can store the dates as metadata, and have the LLM create an array with the date to filter by, and then a query for the vector search.
-
Cerebras-GPT Models Emphasize Open, Royalty-Free AI Access
By
–
@Marktechpost recently wrote an article about the availability of the Cerebras-GPT family of models and mentioned that "It is crucial to have access to open, replicable, and royalty-free state-of-the-art models … for LLMs to be a freely available technology."
-
Cerebras Models Now Available on Hugging Face Platform
By
–
Access the models via Hugging Face: https://
huggingface.co/cerebras Join our Discord: https://
discord.com/invite/q6bZcMW
JVu
… Read the full article here: