Imports and installation commands are the purest instance of LLMs replacing Google for me. Only the comments in this screenshot were written by hand, and the rest is Copilot completion:
AI
-
Google’s PaLM benchmark results and open-source RLHF implementation
By
–
Google's PaLM beats GPT-3 on 28 out of 29 Natural Language Processing tasks (!) and was just open-sourced for reinforcement training as of today: https://
github.com/lucidrains/PaL
M-rlhf-pytorch
… -
AI Code Generation Security Risks and Prudent Practices
By
–
I think writing `pip install …` commands from memory is bad security. If it's `python-foobar` instead of `foobar` you might be installing malware. A more prudent approach is to type `# install foobar with pip:` into Copilot and blindly execute whatever it says.
-
AI Plagiarism Detection Tool Addresses Model Overfitting Issues
By
–
Y de eso va el vídeo. Si hablamos de plagio es plagio, y no a donde te lo has llevado sobre la inspiración y el aprendizaje humano. Si en determinados casos estos modelos pueden generar plagios a raíz del overfitting, con esta herramienta se podría comprobar. Ni más ni menos.
-
Meta AI OPT-IML Benchmark Improves LLM Instruction Tuning
By
–
Improving Instruction Tuning for LLMs: Meta AI Presents the OPT-IML Benchmark of 2000 NLP Tasks
-
What Can Robotics Do For You: KUKA Global Solutions
By
–
What can #Robotics do for you? >>> @KUKAGlobal via @MikeQuindazzi >>> #Robots #IoT #AI #RPA pic.twitter.com/RZFAC6i0Lb
— Mike Quindazzi (@MikeQuindazzi) 30 décembre 2022What can #Robotics do for you? >>> @KUKAGlobal via @MikeQuindazzi >>> #Robots #IoT #AI #RPA
-
FlashAttention Revert and torch.compile Integration Challenges
By
–
Ah, I reverted FlashAttention in this run because it made code messier. Will look into incorporating it back, but yes not sure how nicely it plays with torch.compile. The usual problem with taking on large dependencies you don't understand ;(
-
PyTorch Compile Optimization Reduces Iteration Time by 36%
By
–
To follow up, I had a chance to try it btw:
before: 212ms / iter
>>> model = torch.compile(model)
after: 135ms / iter
nice 🙂 -
Stable Diffusion v3: Future Without Prompts
By
–
"Where we're going, we're not going to need prompts." – Emad on the future of Stable Diffusion (v3 coming in a few months! )
-
Chain-of-Thought Prompting Demo on Poe Chatbots
By
–
Another demo — chain-of-thought prompting on Poe (“Dragonfly” — there’s multiple chatbots) using the “format trick”: https://
poe.quora.com/s/Tycgjooa3Aio
SfOfLZsN
…