One of the biggest problems with "AI" is it never does what you tell it to do, especially when walking on controversial grounds. It always wants to be your mommy and sanitize everything. This post isn...
RLHF is bullshit. It is only at all used because of cloud provider liability (because the tech is primitive with memory and expensive with compute) and it makes the robot prone to favoring shortcuts (that is why claude is notorious for this, their RLHF is the most babying).
For engineering work on the edges of the known it wastes incredible amounts of time. 1M context windows help you neutralize it.
For engineering work on the edges of the known it wastes incredible amounts of time. 1M context windows help you neutralize it.
1💯1