Llama 3
3 mentions across 2 people
Visit ↗All mentions
“If you look at pre-training, if you look at Llama 3 for example, I think it's trained on 15 trillion tokens.”
Andrej Karpathy on the "Decade of Agents" and Future of AI ↗
“You released um llama 3 3.3 is that right the latest update um that powers uh meta I talk about um what it does and I'm going to ask you to compare it to other models out there and be honest like how good is it compared and how do you look at that scientists that need to be honest yeah um okay I mean the main difference between llama and most of the other models is that it's it's free and open right open source”
Democratizing AI: Yann LeCun on Open Source, AGI, and Regulation ↗“He and Meta AI have been big proponents of open sourcing AI development, and have been walking the walk by open sourcing many of their biggest models, including LLaMA 2 and eventually LLaMA 3.”
Beyond Autoregressive LLMs: The Case for World Models and Joint Embedding ↗