Kinda irked by this post mate. The article doesn't warrant your addition of "takedown" / "apparent success" _and_ doesn't convince me. Nothing here was underhanded - these trade-offs have all been explicitly known and discussed - and even then the article only notes two of these.
takedown of OpenAI’s apparent success at ‘Dota 2’https://apple.news/A45CaowNkR7GQ8x92qTIbdg …
-
-
-
The first, that it should use vision rather than an API, is essentially irrelevant imo. What the API provides could be produced by a vision model, the primary reason to avoid it is that it'd be a waste of training time _plus_ rendering the DotA client would be insane overhead.
- 4 more replies
New conversation -
-
-
I'm not sure "cheating" is the right word. In most things, computers have an inhuman advantage, and humans have an incomputer advantage. I'd say instead that the AI has features that limit generalizability.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Like AlphaGo, OpenAI-Five will eventually use strategies that humans will at first frown upon and then understand. Other Dota2 AI strategies will be beyond human understanding.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Kudos to a balanced OpenAI vs Humans matches review. Experience from AlphaGo etc suggests that once an AI reaches a certain proficiency level it's only a matter of relative short time before the AI excels to superhuman performance. OpenAIFive seems close to that leap
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.