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.
As a security researcher who is into OSINT, HIBP is my first go to when obtaining an email address of interest. If it's found, it immediately helps me know which leaked DBs to go grep through and find more info about the target email addy.
Obtaining and storing TBs of leaked databases is another part of the puzzle that is always growing and a bit more complex.
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 different.
While I understand the frustration, I assure you that the rest of the code is functional. This was a simple oversight and should be a trivial fix. I appreciate your feedback and understanding.
Thanks for digging this detail out! I'm a bit disappointed since I was looking forward to playing this with friends again (fond memories), but I can totally understand how the dev might not have the necessary time to implement this.
If you want to play online, I recommend checking JJ2+, jazz2online.com and the discord link there. It's fairly easy to setup. You just need the base game, which is available on GOG and runs perfectly fine one modern Windows computers. Check gog.jj2.plus website for the installation process.
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 technique is really hard in PyTorch / Tensorflow. This is because:
1. Jax has vmap. (PyTorch does now too, but it is far more recent).
2. There are RL environments that others have written in pure Jax (see the blog post for four different repos of RL environments)
3. As m00x hints to, Jax replicates Numpy's API. This makes it way easier to use for non-neural network programming (e.g. RL environments).
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 Jax.
While there is work on putting RL environments on accelerators, the main speedup from this work comes from also training many RL agents in parallel. This is largely because the neural networks we use in RL are relatively small and thus don't utilize the GPU very efficiently.
While this was always possible to do, Jax makes it way easier because we just need to call `jax.vmap` to get it to work.
It makes it really easy to make games for reinforcement learning. I worked on it a bit over summer, so if you have any questions, feel free to reach out to me.
We do indeed use Unity! Somehow I was aware of ml-agents, but didn't realize it was a "gymification" library. I thought it was a framework for running stuff within the Unity editor, but seeing that it allows things to be run from a normal python environment, that's awesome. Thanks for making me look at the README and documentation closer.
And here I was thinking I would need to write a native dll wrapper or wait till my next game project to include necessary bits from the outside.
