No, AI Won't Replace You

Written by mcmurchie | Published 2023/03/22
Tech Story Tags: chatgpt | artificial-intelligence | machine-learning | gpt-4 | ai | future-of-ai | productivity | technology

TLDRRecent developments in AI has caused a bit of mass hysteria and panic in the social sphere. This month i've been asked things like "how long have I got left?" and "are we going to be like pets to them?" The digital and intellectual domain is a little more fuzzy however, so I thought rather than making useless predictions, I wanted to share the key areas you can and should focus on to stay ahead.via the TL;DR App

Image from Bosstown Dynamics a comedic play on BostonDynamics working on smart robotics.

Hype aside, recent developments in AI has caused a bit of mass hysteria and panic in the social sphere. This month i've been asked things like "how long have I got left?" and "are we going to be like pets to them?"

While no doubt a lot of it is in jest, there is certainly an increasing level of tension between what the media reports AI can do, and what it can actually do.

First, let’s get the main thing out the way, LLMs like ChatGPT & BARD aren't AGI (artificial general intelligence), they are just complex Sequence Transformers. They don't actually understand what you are saying, they have no logical reasoning skills (just because a Parrot sounds smart, doesn’t mean it has a clue what it’s talking about).

It doesn’t actually know that 1+1=2, just that 1+1 is followed by =2 most of the time. Microsoft claimed GPT4 had 'Sparks of AGI' in a paper masquerading as science, but don’t let that fool you, GPT4 only generates text, there is no internal quality control or self correcting for it to refactor its answer based on new facts - this means that if you don’t have domain expertise, trusting it will put you at high risk.

Which is why they plaster warning limitations on the front page ‘my occasionally generate wrong answers,’ which is an understatement.

Bricklayers, chefs, plumbers and hairdressers are unlikely to be automated in the next 30 years, so if you work in a highly manual field, you can relax for now.

The digital and intellectual domain is a little more fuzzy however, so I thought rather than making useless predictions about what's in and what's out, I wanted to share the key areas you can and should focus on to stay ahead:

  • Creativity
  • Higher level reasoning
  • Soft Skills
  • Leadership
  • High fidelity/dexterity/intricate bespoke craftsmanship
  • Technical Design & Architecture

CREATIVE ENDEVOURS

Neural Networks don't just master things they have seen before, they fit to a curve - this means they learn trends well. Where you will excel is if you become a trend setter, focus on original content, finding personalised niches in whatever product you are interested in working on - demand will spike in the domain of hyper personalisation.

HIGHER LEVEL REASONING

AI doesn't obliterate the 'things to do' pie, rather it expands the pie by opening up new capabilities, you need to expand your mind to 'what problems will we face once we have automated menial work?' Spoiler alert: it requires being vision driven rather than feature driven.

If becoming a hyper 10x developer isn't for you, then look into cross functional IT be it leadership or solutionising, AI hasn't even begun to touch this area.

MAKING THINGS WITH YOUR HANDS

Some things to consider, as the world ages (East and West are suffering from mass ageing, and collapsing demographics) - this means as consumption plummets, the demand for bespoke, tailored products will skyrocket. Think fashion, personality, trend setting, countries like Italy will pull ahead, so much is hand made there.

I'm stopping here for now, if you like what you see let me know and I will finish the second part.

For those interested in actually how to take advantage of the latest wave of AI here is a short on prompt engineering.

https://youtu.be/V28CU8LEXlU?embedable=true

P.S. ChatGPT did not write this.


Written by mcmurchie | Head of Data and DevOps: focusing on building non-mainstream projects to learn more about the world and share ideas.
Published by HackerNoon on 2023/03/22