Most likely was told its for testing data. Hence has to look as real/broken/nuanced/etc as possible
CODE
-
Automatic Generation Saving to Hugging Face Dataset Repositories
By
–
Now you can save all generations automatically to a private/public huggingface dataset repo! No changes needed. If your output path is a repo and if you are logged in using huggingface-cli, the generations will be saved to your hf account!
-
GPT-3 App for Intelligence Community OSINT Testing
By
–
This app uses GPT3. If you are a professional in the intelligence community I would appreciate you testing it out. Just beware of limitations and remember, it is a proof of concept! https://
unrestrictedintelligence.com #GPT3 #OpenAI #OSINT #ChatGPT -
Multi-Agent Architecture: Combining DB and Search Tool Patterns
By
–
super interesting. do you imagine a common query pattern to need both the DB and search tool? or will most queries be one or the other? if separate, you could almost make an agent for each tool, and then use those agents as tools themselves in a meta-agent that wraps them
-
Android 13 Adopts Rust for Memory Safety Security
By
–
“In Android 13, about 21% of all new native code (C/C++/Rust) is in Rust. There are approximately 1.5 million total lines of Rust code.” https://
security.googleblog.com/2022/12/memory
-safe-languages-in-android-13.html
… -
Emoji Search API Fixed with Cheaper Ada Model
By
–
https://
emojisearch.app was broken late last year. It has been fixed now and should run faster than before. Also, the backend has been updated to use our latest and cheaper `text-embedding-ada-002` model. -
Transformer Inference Optimization: Reducing Computational Costs
By
–
Large Transformers are powerful but expensive to train & use. The extremely high inference cost is a big bottleneck for adopting them for solving real-world tasks at scale. Check out my new post on some ideas on inference optimization for Transformers:
-
Library Feature Request for Standardized Implementation
By
–
I hope you do add it at some point – it's a pretty slim library, and it provides a feature pretty much everyone needs, and it's something that needs to be done in a consistent standard way across projects.
-
Neural Networks: Zero to Hero Series – Building Networks from Scratch
By
–
(This will be part of my ongoing series Neural Networks: Zero to Hero https://
karpathy.ai/zero-to-hero.h
tml
… , on building neural networks, from scratch, in code. I have tweeted some of these videos individually already) -
Future Plans for GPT-2 Implementation and Educational Content
By
–
I'd like to continue to make it faster, reproduce the other GPT-2 models, then scale up pre-training to bigger models/datasets, then improve the docs for finetuning (the practical use case). Also working on video lecture where I will build it from scratch, hoping out in ~2 weeks.