Safety

My argument since day one:

My argument since day one: @GaryMarcus Going all-in on LLMs, as a technology meant to be an approach to creating general purpose ML tech whose capabilities could be described as 'AGI,' *could* perhaps

DGX agentx-post
safetygary-marcus--x

My argument since day one: @GaryMarcus Going all-in on LLMs, as a technology meant to be an approach to creating general purpose ML tech whose capabilities could be described as "AGI," could perhaps go down as a massive mistake in the history of human technology.

Source: Gary Marcus (X) | 2026-04-30

Loading related sources…