'We support the work of those who are trying to limit the harm generative AI is doing to videogames and our world, and apologise that Big Walk’s LLM usage may not meet their standards'
I think the example cases they’ve provided are pretty good example of where an LLM can actually be useful. For example, if you need to find and fix a bug in third-party code, it can be an absolute pain, as just getting a basic understanding of an unknown codebase by yourself could take days or weeks. An LLM can analyze the code in seconds and if not fix the bug, at the very least point out locations where to look for it. It’s not necessarily about telling the LLM to overcome the technical challenge by itself, but it can definitely assist in it.
Except that’s covered in the article. It was able to provide some semblance of a solution and then they were able to hammer that into an actual solution. So the assistance provided by the AI, while not absolute, was demonstrably useful.
Considering their games have never used online multiplayer before, I’m guessing the bugs were to do with netcode, which is infamously tricky to get right, requires a huge amount of boilerplate and exception handling, but is mostly a solved problem; while being so tedious to debug and implement it causes programmers souls to leave their body. I think those are the kind of tasks LLMs are most suited for, actually
“Difficult technical challenges and bugs” is what I find AI is the worst at in my experience.
I think the example cases they’ve provided are pretty good example of where an LLM can actually be useful. For example, if you need to find and fix a bug in third-party code, it can be an absolute pain, as just getting a basic understanding of an unknown codebase by yourself could take days or weeks. An LLM can analyze the code in seconds and if not fix the bug, at the very least point out locations where to look for it. It’s not necessarily about telling the LLM to overcome the technical challenge by itself, but it can definitely assist in it.
Except that’s covered in the article. It was able to provide some semblance of a solution and then they were able to hammer that into an actual solution. So the assistance provided by the AI, while not absolute, was demonstrably useful.
I’d recommend reading the article.
Considering their games have never used online multiplayer before, I’m guessing the bugs were to do with netcode, which is infamously tricky to get right, requires a huge amount of boilerplate and exception handling, but is mostly a solved problem; while being so tedious to debug and implement it causes programmers souls to leave their body. I think those are the kind of tasks LLMs are most suited for, actually
You conveniently dropped “to help work through” here, so now it implies they let AI do the work.