Makes you wonder if LLMs are the best way to model the world at all…
@hardmaru
-
Demis and the Legendary Syndicate Game from the 1990s
By
–
Makes sense. Demis worked on the original Syndicate game which was a legendary PC game from the 1990s, about an executive at a multinational corporation using cyborgs with AI-implants to achieve world domination.
-
ZeroGPU Infrastructure Success at Sakana AI Labs
By
–
ZeroGPU is a fantastic example of great AI infrastructure developed by @HuggingFace
. At @SakanaAILabs we’ve already been using it to showcase models like EvoVLM and EvoSDXL and it works like a charm. -
Congratulations on autonomous world models for vehicles
By
–
congrats, @alexgkendall
! looking forward to seeing your autonomous world models in every car 🙂 -
KAN: Kolmogorov-Arnold Networks – Questioning Fundamental ML Building Blocks
By
–
KAN: Kolmogorov-Arnold Networks https://
arxiv.org/abs/2404.19756 This paper is so fun to read. We need more works like this, questioning our fundamental building blocks. -
Key to Successful Image Generation: Avoid Typical AI Look
By
–
The key to using image generation AI successfully is to produce images that don’t look like the typical AI-generated images.
-
Community-Created PEFT Fine-Tuned Llama-3 Models Expected
By
–
I’m looking forward to the tens of thousands of PEFT’ed Llama-3 70B and 400B models with various new superpowers that will be created and released by the community.
-
NEAT Agent Playing Mario Kart 64
By
–
I also love this other NEAT agent for Mario Kart 64 from a while back: https://t.co/v7gg8nGljL
— hardmaru (@hardmaru) 28 avril 2024I also love this other NEAT agent for Mario Kart 64 from a while back:
-
Parameter-Efficient Fine-Tuning Methods for Large Language Models
By
–
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey PEFT algorithms are useful for dealing with LLMs with high parameter counts, as even fine-tuning these models from scratch can be computationally expensive and resource-intensive. https://
arxiv.org/abs/2403.14608 -
Sometimes Avoiding Auto-Differentiable Methods in Development
By
–
true-sometimes I try not to use auto-differentiable methods 🙂