Just open-sourced our screaming-fast BPE tokenizer:
@gdb
-
Hill Climbing in Billion-Dimensional Spaces: Deep Learning Training
By
–
Training of deep learning models by “hill climbing” seems like it should be impossible because of our intuitions from 3D life. Turns out they don’t prepare us to understand what’s possible in billion-dimensional spaces.
-
New Embedding Model Outperforms Previous Best at 99.8% Lower Cost
By
–
Just released a new embedding model which outperforms our previous best one while being 99.8% cheaper:
-
Emacs Users Face Unique Challenge With Broken Control Key
By
–
Few technical experiences are more difficult than being an Emacs user with a broken ctrl key.
-
Chat Interface GPT-3.5 with External Integrations
By
–
Another angle on a chat interface to GPT-3.5, together with external integrations to make it even more useful:
-
ML Performance Engineering: Patience with Job Launch Times
By
–
A surprising amount of machine learning performance engineering starts by getting fed up with how long you spend waiting for your job to launch.
-
Power User Interface and Prompt Engineering Experience Enhancement
By
–
Feedback greatly appreciated! Would a “power user” interface to the same model restore the magic, or does the model itself feel less fun for serious prompt engineering?
-
ChatGPT: Alignment Breakthrough Beyond Base Model Capabilities
By
–
Exciting but overlooked that ChatGPT is primarily an alignment advance—the base model (GPT-3.5) has been available in publicly for many months, but making it into a useful chat system required significant strides with reliably following the intent of the developer and the user.
-
OpenAI launches ChatGPT conversational AI system
By
–
Just launched ChatGPT, our new AI system which is optimized for dialogue: https://
openai.com/blog/chatgpt/. Try it out here: https://
chat.openai.com