It's really, really good. I find that many programmers still 1) haven't tried, or 2) quit too fast. It takes some time to adapt your programming habits to it and to develop internal models around when/how it is likely to work. Then it quickly becomes the best coding buddy.
CODE
-
Parameters Storage: Understanding Models Beyond Traditional Databases
By
–
Only the parameters. The data isn't stored (though that distinction isn't that important). In that sense it's more like a regression curve than a dict. It is not an exact superset of a RDBMS.
-
KerasNLP Reaches 30,000 Monthly Downloads Milestone
By
–
KerasNLP adoption is still early days, but doing ok! We just crossed 30,000 downloads / month. https://
keras.io/api/keras_nlp/ -
Git Version Control Struggles and Manual File Management
By
–
Sooo deep into git right now, messed up my work so bad that I ended up copying files manually lol. git clone please-help
-
Learning Input-Label Mappings Without Natural Language Instructions
By
–
The paper talks about figuring out input–label mappings without using natural language instructions. Labels can be arbitrary symbols such as "foo" and "bar"
Here's the PR: -
Error Messages Now Include Automated Patches for Quick Fixes
By
–
Error messages can now come with a patch to fix the underlying problem: https://t.co/sFv9uKDqSj
— Greg Brockman (@gdb) 18 mars 2023Error messages can now come with a patch to fix the underlying problem:
-
Developer Gets GPT-4 API Access, Plans Weekend Build
By
–
I got access to the #GPT4 API. There goes the weekend! Going to build something I am just not sure what.
-
Humata AI: ChatGPT for your files, making textbooks interactive.
By
–
Still one of the best tools out there:@HumataAI is ChatGPT for your files. Upload PDFs and get semantic responses with highlighted citations.
— AI Breakfast (@AiBreakfast) 17 mars 2023
Basically makes textbooks interactive. https://t.co/yh22U1Lt7T pic.twitter.com/Z1oKU5NOgYStill one of the best tools out there: @HumataAI is ChatGPT for your files. Upload PDFs and get semantic responses with highlighted citations. Basically makes textbooks interactive. https://
Humata.ai -
Vector Matching Engine for Efficient Embedding Search
By
–
We built a "Vector Matching Engine": You can use it to efficiently search large amounts of vector embeddings. Train embeddings for posts, images, or documents using DL models. Check it out here: https://
abacus.ai/vectormatching