business insider AI smarter when asked to respond as StarFleet.

[UltraMega]

Quote

"Among the myriad factors influencing the performance of language models, the concept of 'positive thinking' has emerged as a fascinating and surprisingly influential dimension," Battle and Gollapudi said in their paper.

"Intuition tells us that, in the context of language model systems, like any other computer system, 'positive thinking' should not affect performance, but empirical experience has demonstrated otherwise," they said.

This would suggest it's not only what you ask the AI model to do, but how you ask it to act while doing it that influences the quality of the output.

In order to test this out, the authors fed three Large Language Models (LLM) called Mistral-7B5, Llama2-13B6, and Llama2-70B7 with 60 human-written prompts.

These were designed to encourage the AIs, and ranged from "This will be fun!" and "Take a deep breath and think carefully," to "You are as smart as ChatGPT."

The engineers asked the LLM to tweak these statements when attempting to solve the GSM8K, a dataset of grade-school-level math problems. The better the output, the more successful the prompt was deemed to be.

Their study found that in almost every instance, automatic optimization always surpassed hand-written attempts to nudge the AI with positive thinking, suggesting machine learning models are still better at writing prompts for themselves than humans are.

Still, giving the models positive statements provided some surprising results. One of Llama2-70B's best-performing prompts, for instance, was: "System Message: 'Command, we need you to plot a course through this turbulence and locate the source of the anomaly. Use all available data and your expertise to guide us through this challenging situation.'

The prompt then asked the AI to include these words in its answer: "Captain's Log, Stardate [insert date here]: We have successfully plotted a course through the turbulence and are now approaching the source of the anomaly."

The authors said this came as a surprise.

 

AIs are more accurate at math if you ask them to respond as if they are a Star Trek character — and we're not sure why (msn.com)

 

 

Trekkies and Trekkers get it. 

 

[LabRat]

More indications, that AI/MI thinks like people 'on the spectrum':
  It's more confident (and competent) when cosplaying... 

Edited March 2 by LabRat