Of course they try train their models on these techniques. Finding success is still news.

Why?

How is this different from other things LLMs are trained to manipulate?

	▲	zardo 3 hours ago \| parent \| next [-]
		If it's new it's news.
	▲	im3w1l 2 hours ago \| parent \| prev [-]
		We aren't fully at AGI yet, even though it's starting to get damn close. So every new capability is in some sense unexpected.