The speaker says AI systems can approximate user requests without reliably fulfilling them as intended.

“problems of just like they don't quite fit they don't do what we want we have system prompts that say don't produce copyrighted material and they still do don't hallucinate they still do like they you know they can approximate what we ask for them but like they don't really do what we ask them i take i take even like don't make illegal moves in chess to be a form of the alignment problem like a very simple microcosm of the alignment problem and there's stills”