Making AI Sound More Like Us
Generated w/Dall-E

Making AI Sound More Like Us

Simplifying Output Through the Flesch Reading Score

Ever felt like chatbots or AI programs try too hard?

They often use big words and long sentences, adverbs, passive voice and hyperbolic language that might sound fancy but feel unfriendly.

Some of the cringe-inducing regular words I see appearing frequently include: "Pivotal" "Transformative" "Paramount" "Navigating" "Fostering" and "Crucial".

I bet you noticed some regular AI words like these too, let me know in the comments what the dead giveaway words you spotted that immediately give you a clue that you're reading something LLM-generated.

It's like having a conversation with a textbook. The truth is, when we chat, whether with friends or colleagues, we keep it simple. That's what makes our conversations feel natural and easy to follow.

And simple language matters. In the USA, 53% of adults have literacy levels below that of a 6th grader. But with the default "voice" of LLMs you can come off sounding, well, robotic and tryhard, even unreadable. Worse still, the wider international audience of non-native English speakers may not be able to catch your drift.

Now, there's a way to make AI sound more like us: By using the Flesch Reading Score. This score tells us how easy it is to understand something written. The higher the score, the simpler the text. By aiming for a score of 80, 90 or above, we can make AI write in a way that's easy and pleasant to read - almost like it's coming from a friend.

Why does this matter? The main point of using AI, whether for work, learning, or just fun, is to make our lives easier, not harder. When AI talks like a human, using straightforward language, we can understand it quickly and use it more effectively.

It's about making technology work for us, not the other way around.

In practice, this means programming AI (via Custom Instructions or the Prompt itself) to choose simpler words and shorter sentences. It's like teaching it to communicate in a way that's natural for us. This doesn't just make AI more helpful; it also makes our interactions with it more enjoyable.

By focusing on making AI's language clear and straightforward, we're taking a big step toward technology that truly fits into our lives without being so annoying. It's not just about making machines smarter; it's about making them more relatable and easier to use.

So, the next time you come across a piece of writing from AI, imagine how it would sound if it scored 80, 90 or above on the Flesch Reading Score. Give it a try.

Wouldn't it be nice if all technology communicated that clearly? It's a goal worth aiming for as we blend technology into our daily lives.

To execute this hack, GPT 4 pro users can add the following sentence to custom instructions, and for the rest of you using the free version of GPT, you can simply add this to any prompt you want to sound more.... human!

Let me know how you get on!

"Write at a Flesch Reading Score of 80 or higher"
Greg Moran

Multi-Exit Founder | High-Performance Startup Coach | Author, “The Adaptive Innovator” | Founder @ The Founders Collective I Venture Investor

10 个月

Tried this out and it's fantastic! Thanks Michael!

回复
Michael Wright

CMO Hunter | ex-WPP | 2x Founder, 1 Exit | Connector

11 个月
回复

"Write at a Flesch Reading Score of 80 or higher" thanks Michael Wright - or just write your own content which should be authentic and hopefully readable; regardless good idea to run FRS (another 3 letter achronym, and welcome to adtech ;)

回复
Ali Zein Kazmi

Full-Funnel Marketing Strategy Expert | Creativity and Innovation For Growth | Co-Host of ShanghaiZhan China Marketing Podcast

11 个月

Always need to do a second take on the stuff I use AI for. Bryce and I use GPT loads to accelerate questioning our guests but need to "dumb down" the questions so that it's more friendly to both our listeners and our guests. On the other hand it's worrying how the use of any language English, Mandarin Chinese or Urdu is losing eloquence and sophistication as humanity defaults to simplicity and sometimes confuses it with stupidity. Lets all read more. :)

"Grappling" "Cornerstone".... I am not smart enough to string together AI word soup.... It also does not know my voice, but cleans up a lot of my ranting I do when I am, well, ranting..... AI does not have the personal problems I have... so there is that.

要查看或添加评论,请登录

Michael Wright的更多文章

  • What CFO's Want from Marketing in 2025

    What CFO's Want from Marketing in 2025

    Takeaways from CEO & CFO Commentary Across Top Brands We already know it. Marketing is about measurable impact.

    4 条评论
  • Optics, Politics & Lionwashing

    Optics, Politics & Lionwashing

    I read a TechInAsia article recently discussing the trend of 'Singaporization'—how some companies are moving their…

  • Is Marketing Eating the World? Or Eating Itself?

    Is Marketing Eating the World? Or Eating Itself?

    Everyone is Busy Marketing What used to be a small department of designers, writers, and people making fancy PPTs is…

  • Addressing a lack of feedback in the hiring process

    Addressing a lack of feedback in the hiring process

    Since launching Taligence in late 2023, we've had the privilege of speaking one-on-one with hundreds of senior-level…

    1 条评论
  • We built a palm-reading GPT just for the lulz

    We built a palm-reading GPT just for the lulz

    ChatGPT pro users can get a reading immediately at the link. Ah, the origin story of Palm Reader Career, a GPT brought…

    2 条评论
  • Our GPT can tell if you're a good fit for Product Management*

    Our GPT can tell if you're a good fit for Product Management*

    *or any other career path! If you've been following me on Linkedin, you might already know I'm at the end of a…

    5 条评论
  • Why I left a job I loved

    Why I left a job I loved

    This month marks the end of my 12-year journey at WPP as the Global Head of Talent Acquisition Innovation & Operations.…

    124 条评论
  • There are 2158 ways you can contribute

    There are 2158 ways you can contribute

    I could never have imagined that our GroupM Talent Acquisition teams around the world would have hired 7,000 bright…

    2 条评论
  • How GroupM puts purpose upfront for our clients

    How GroupM puts purpose upfront for our clients

    Corporate performance, investment performance and Environmental, Social and Governance (ESG) issues are inextricably…

    2 条评论
  • Our differences make us stronger

    Our differences make us stronger

    Have you ever looked for ways to 'get your life back'? Did you find them? Belle did both. At the height of her teen…

社区洞察

其他会员也浏览了