I love this site! Though I do wonder how much this site also helps amateur hackers find where to search for a specific person's password. One way to deal with it could be to email the person their pwns.
Author here! Thanks for pointing that out. The correct model name is indeed "gpt-4" instead of "gpt_model = 'gpt4_20231230_1106preview'". We were previously using an Azure endpoint, which is why the model name is…
Seems like the creator says it would take 300+ hours and they don't have time (on their discord).
The baseline we are comparing to is standard RL training that is widely used in academia. The technique mentioned in the blog post is not widely used amongst researchers. The reason we write about Jax is that doing this…
Indeed the devil is in the GPU! Jax and its ecosystem just make it much easier to use the GPU.
Author here! I didn't realize this got posted on HN. While indeed we do get a speedup by putting the environments on the GPU, most of the speedup seems to come from the ability to easily parallelize RL training with…
If you're using Unity, I would recommend that you check out Unity Machine-Learning Agents! https://github.com/Unity-Technologies/ml-agents It makes it really easy to make games for reinforcement learning. I worked on it…
I love this site! Though I do wonder how much this site also helps amateur hackers find where to search for a specific person's password. One way to deal with it could be to email the person their pwns.
Author here! Thanks for pointing that out. The correct model name is indeed "gpt-4" instead of "gpt_model = 'gpt4_20231230_1106preview'". We were previously using an Azure endpoint, which is why the model name is…
Seems like the creator says it would take 300+ hours and they don't have time (on their discord).
The baseline we are comparing to is standard RL training that is widely used in academia. The technique mentioned in the blog post is not widely used amongst researchers. The reason we write about Jax is that doing this…
Indeed the devil is in the GPU! Jax and its ecosystem just make it much easier to use the GPU.
Author here! I didn't realize this got posted on HN. While indeed we do get a speedup by putting the environments on the GPU, most of the speedup seems to come from the ability to easily parallelize RL training with…
If you're using Unity, I would recommend that you check out Unity Machine-Learning Agents! https://github.com/Unity-Technologies/ml-agents It makes it really easy to make games for reinforcement learning. I worked on it…