It’s also a lot less interpolatable: If you know that that 15° N, 12° E is land, and 15° N, 14° E is land, you can be reasonably certain that 15° N, 13° E will also be land.
On the other hand if you know that virtually.fiercer.admonishing is land, and you know that correlative.chugging.frostbitten is land, that tells you absolutely nothing about leeway.trustworthy.priority—unless you also happen to know that they’re right next to each other.
(unless what3words has some pattern in the words that I’m not aware of)
No, you’re absolutely right. I actually tried asking GPT-5 about a w3w location and even with web search on it concluded that it was probably sea, because it couldn’t find anything at that address… and the address was in Westminster, London.
So despite words being more of the “language” of an LLM, it was still much much worse at it for all the other reasons you said.
There is also fixphrase.com, where neighboring squares typically share the first three out of four words, so I suspect that might work better in theory, though it’s probably absent from the training data in practice.
It’s also a lot less interpolatable: If you know that that 15° N, 12° E is land, and 15° N, 14° E is land, you can be reasonably certain that 15° N, 13° E will also be land.
On the other hand if you know that virtually.fiercer.admonishing is land, and you know that correlative.chugging.frostbitten is land, that tells you absolutely nothing about leeway.trustworthy.priority—unless you also happen to know that they’re right next to each other.
(unless what3words has some pattern in the words that I’m not aware of)
No, you’re absolutely right. I actually tried asking GPT-5 about a w3w location and even with web search on it concluded that it was probably sea, because it couldn’t find anything at that address… and the address was in Westminster, London.
So despite words being more of the “language” of an LLM, it was still much much worse at it for all the other reasons you said.
There is also fixphrase.com, where neighboring squares typically share the first three out of four words, so I suspect that might work better in theory, though it’s probably absent from the training data in practice.