Since LLMs are sometimes wonderfully useful, and sometimes not, I'd suggest effective use involves figuring out in which cases it's likely to succeed, which it's likely to fail.<p>For example, the mentioned graph has "initial prompt with iterative tweaks", followed by iterations of 'starting from scratch'. -- I don't understand why you'd think "this is an ineffective way of doing things", and then keep doing it.<p>Describing LLMs as "slot machines" seems like the author has no curiosity about the shape of what LLMs can/can't do.