When put to the test in real-world environment, the capabilities don't look as impressive as benchmarks and synthetic tests might indicate. So doubts about actual spatial reasoning capabilities remain.
Aaah, the old benchmarks maxxing argument, having precise and clear definition of what "spatial reasoning" is, what, and most importantly WHY, the benchmarks of choice are would settle this debate, otherweise let's not delve into it.
...poorly? https://youtu.be/ENWVpqtOdRI?t=867
I’m not sure what you are trying to say
When put to the test in real-world environment, the capabilities don't look as impressive as benchmarks and synthetic tests might indicate. So doubts about actual spatial reasoning capabilities remain.
3 replies →
the statement was "can't do"
"doing poorly" is still doing
Careful, you'll have them accelerating their goal posts up to the speed of light if you keep questioning them. That much kinetic energy is dangerous.
Of course this is the same reason LeCun holds very little sway with his words for me, they seem to be terrible predictors of the future.
Aaah, the old benchmarks maxxing argument, having precise and clear definition of what "spatial reasoning" is, what, and most importantly WHY, the benchmarks of choice are would settle this debate, otherweise let's not delve into it.