AI Prompt Engineering Is Dead / Long live AI prompt engineering

According to one research team, no human should manually optimize prompts ever again.

There is an alternative to the trial-and-error-style prompt engineering that yielded such inconsistent results: Ask the language model to devise its own optimal prompt.

this automatically generated prompt did better than the best prompt found through trial-and-error. And, the process was much faster

The optimal prompts the algorithm spit out were so bizarre, no human is likely to have ever come up with them.

The centaur approach is usually better than all human or all AI (at least for a while).

Which makes sense since the two types of “brains” function differently. It’s about finding the optimal combination of the two, not one directing the other.

Speaking of…

Of top-notch algorithms and zoned-out humans

A low-grade algorithm and a switched-on human make better decisions together than a top-notch algorithm with a zoned-out human. And when the algorithm is top-notch, a zoned-out human turns out to be what you get.
…
rather than thinking of the machine as a replacement for the human, the most interesting questions focus on the sometimes-fraught collaboration between the two.

Gold, bitcoin and stocks hit record highs this week. Then came inflation data

investors shrugged off a higher-than-expected 3.2% annual rise in consumer prices and cheered a cooldown in some categories like food prices.
…
US wholesale inflation rose 1.6% for the 12 months ended in February, its fastest clip in months, due to a spike in energy prices.
…
Markets expect the central bank to hold rates steady this month and begin cutting in June or July

Consumer prices climbed 3.2% in February as 2% goal remains elusive

The 12-month inflation rate has been stuck between 3% and 4% since June, hovering just above the Federal Reserve’s official 2% target