Cohere's Command R+ at 111 tokens/s 😲 https://t.co/swbaGtzsID
— Hugging Face (@huggingface) 12 avril 2024
Cohere's Command R+ at 111 tokens/s
GENERATIVE AI
-
Cohere Command R+ Achieves 111 Tokens Per Second
By
–
-
Programming: Thinking Over Syntax, Outsourcing Thinking Fails
By
–
Programming is thinking + syntax. Maybe 90% thinking and 10% syntax. While you can automate away syntax, you can only ever outsource thinking to someone/something that can think. Attempts to outsource thinking to a syntax generator do not end well.
-
LangSmith Achieves SOC2 Type 1 Certification for LLM Development
By
–
We're excited to announce that LangSmith — our solution for LLM application development, monitoring, and testing — has now received SOC2 Type 1 Certification. After a rigorous audit process, LangSmith has been certified to conform to industry best-practices for the protection of
-
NVIDIA Blackwell GPUs Power New Computing and Generative AI Era
By
–
Get an inside look at NVIDIA Blackwell GPUs and the latest data center technologies that are powering the new era of computing and #generativeAI. https://t.co/wjD43zOj3b #GTC24 pic.twitter.com/P2esW3Ej3c
— NVIDIA (@nvidia) 12 avril 2024Get an inside look at NVIDIA Blackwell GPUs and the latest data center technologies that are powering the new era of computing and #generativeAI. https://
nvda.ws/3xyL9Gl #GTC24 -
Instruct Prompt to Base Model Converter Notebook
By
–
If you'd like to try it or contribute, check out the Github repo. Use the `Instruct_Prompt_>_Base_Model_Prompt_Converter.ipynb` notebook.
-
Claude 3 Prompt Engineering for Base Models Guide
By
–
This repo was inspired by this article I wrote, explaining how to prompt Mixtral 8x22B. Turns out, Claude 3 is quite good at prompting base models, if you set it up correctly.
-
Claude 3 Opus now available on Google Cloud Vertex AI
By
–
Claude 3 Opus, our most capable model for highly complex tasks, is now in public preview on @googlecloud
's Vertex AI. The addition of Opus means businesses can optimize intelligence, speed, and cost across the full Claude 3 model family. Get started: https://
cloud.google.com/vertex-ai -
AI Comedy: When Machine Humor Falls Emotionally Hollow
By
–
this was almost the first computer program to ever intentionally laugh (and i'm easy to make laugh) but sadly, no; i thought this was pretty dumb; it really gets the tone of standup right, though, the pauses and the cadence and everything, but the humor was really hollow
-
Middle Managers: Key to Unlocking Generative AI Potential
By
–
Middle managers hold the key to unlock generative #AI
by Emily Field @bryanahancock @LareinaYee @McKinsey Read more: https://
buff.ly/3QGuZQT #ArtificialIntelligence #ML #MachineLearning cc: @pbalakrishnarao @yvesmulkers @kuriharan -
OpenAI Team Delivers Exceptional Customer Support
By
–
love watching the openai team rally to provide great support for a customer