Authenticity in an AI World

Welcome to this weeks LinkedInformed. This is also week 1 of my experiment with AI. I transcribed the full podcast recording and asked ChatGPT to summarise it in less than 1500 words. What it came out with was completely hopeless and unusable! So it's not quite the golden ticket some people are making it out to be!

That said, I did use it for the headline and I will continue to experiment with it on other things but I don't think it's capable of producing the show notes, at least not yet!

On the other hand the above image was produced on dall-e-2 by asking for an image of a 'woman peeking from behind a robot'...a pretty impressive result I reckon!

This week I cover;

• 4 new features/changes to LinkedIn
• My assessment of Tomer Cohen 's recent podcast interview
• LinkedIn search parameters are unreliable
• Some interesting LinkedIn stats
• Do LinkedIn really know a good profile when they see one?
• Authenticity becomes more important amid AI advancements
• Post of the week

LinkedInformed is a weekly podcast which you can listen to on Apple or Google podcasts, Amazon music or Spotify (below). If you subscribe on your podcast player app, the next episode will automatically download to your phone.

New on LinkedIn

Engaging with a post in the feed triggers a prompt to either read further content from that person, if you are already following them.

Or it encourages you to connect to them if they are not a connection

What I find odd about this is that the prompt is to connect, not to follow yet LinkedIn seem to be encouraging following these days. In addition, Lara above has creator mode and therefore the primary option on her profile is to follow her. In addition, this whole action is based on content, so surely following is the most appropriate prompt, not connect.

I strongly suspect this is not intentional and merely another example of a lack of joined up thinking at LinkedIn.

In addition, I have noticed this occasionally appearing under posts on what seems to be a random basis;

So what happens if I vote yes, does the algorithm push the post out to more people? Conversely will choosing no adversely affect the post or even the author?

At this stage, I suspect LinkedIn are just experimenting but if this became mainstream, it could be very impactful. My guess however, is that this will be mostly ignored and LinkedIn will drop it.

Also;

Post scheduling has come to mobile, at least iOS anyway;

How are you getting on with post scheduling. Is this new feature working well for you?

Have invitation restrictions changed?

For quite some time now people have been working on the assumption that LinkedIn limits invitations to 100/week. This has been a arbitrary figure to me because I can't ever see a reason to get anywhere near that number but recently

Melanie Goodman posted this;

I was never sure about the 100 figure in the first place, I suspect it was invented by companies selling LinkedIn automation tools as a means to reassure their customers that they have their back covered and that no harm would come to their account if they used their product - the reality was that many people have been banned for using automation and this may partly be due to the fact that the limit has always been account dependant, not a fixed figure. It's logical that someone who gets a 95% acceptance rate would be allowed to send more invites that someone who achieves 50%!

Company pages can now follow other pages.

This certainly isn't a feature I will be using but if you are one of those company page admins that likes to engage anonymously, or you just want to snoop on what your competitors are putting out on LinkedIn, you might find this useful.

The problem is that changing your page to feed to 'following' is not sticky so it just reverts back to page posts on every page refresh.

Tomer Cohen appeared on the 'Decoder podcast' recently and I finally got around to listening to it this week, it's always interesting to listen to senior LinkedIn execs (and they don't come much more senior than Tomer) talk because we can often gain valuable insights that you don't get from the PR diluted articles they post here.

The interview lasts 1hr 17 mins so to save you the time, I have summarised my thoughts below;

• Tomer hints that they do not consider the 'time spent on LinkedIn (session time)' to be a key metric. This is at odds with how investors view businesses like LinkedIn and I'm a bit sceptical - after all, the more time we spend here, the more ads we see and the more likely we are to get a job through LinkedIn, two very important revenue streams for LinkedIn.
• Skills are how most companies recruit these days and are now more important than traditional qualifications. 50% of recruiters use skills as a search filter but he also conceded that skills validation is still a challenge, despite features like skill assessments.
• People getting hired through Linkedin was described as a 'true north' metric! Again showing that, despite most of us seeing the network differently, LinkedIn still focus on recruitment more than anything else.
• LinkedIn now have a big team working on assessing 'knowledge exchange' and this is a focus for LinkedIn now. My reading of this is that they have decided to back away from monetisation of content in favour of encouraging members to make money by winning business through demonstrating their knowledge. Does this mean that the algorithm will favour posts that provides advice and expertise?
• Further to the above point, he seemed to be in favour of cold pitching on LinkedIn. This is a huge mistake in my opinion and seems very narrow-minded short term perspective to take. I believe that cold pitching permanently damages the credibility of the network.
• AI will have a huge impact, especially when members use it to write their profiles. Tomer suggests that those smart members will realise that they need to use video much more in their profiles and content.

LinkedIn search is unreliable. Irina Shamaeva ???? explains how we shouldn't rely on solely using " " for searches on LinkedIn, she managed to get the following reply from LinkedIn Engineering (not the hapless Help centre!)...

"Double quotes around a phrase producing unexpected results. “recruiter” behaving differently from recruiter (no double quotes).

This is an intended behavior and highlights what our double quote functionality actually does. It is true that using double quotes forces the system to do an exact text match. However there is slightly more to it. When no double quotes are used, the system tries to understand the meaning of your search terms as well as what portions of a job it should search for to find those terms. The system does not always use an exact text match here as not every single job with the occurrence of a search term is actually relevant. Some (not all) of the places we look at are the job’s title, description and desired skills. Our search then decides which of those are the most relevant and displays the results to you. This means you will not see every single job with the words “sourcer” or “recruiter” in the title/description/skills/etc., but rather, you will see all the jobs that our system thinks are for someone that is a sourcer or a recruiter. For example, a software engineering job that has a description stating “talk to our recruiter to learn more” is likely not a good job search result.

You can read the full article here

LinkedIn released some interesting stats this week in this article, most notable were;

• 11 million now have enabled Creator mode
• 22% year-on-year increase in post views
• 25% increase in public conversations (comments)
• 25% increase in personal posts
• 176% more scheduled events
• 75% more spontaneous events
• 39,000 skills are now listed

With regards to scheduled events it appears that 3rd party Livestream providers are not currently able to schedule events. This might be a glitch but it could also be that LinkedIn are going to release native scheduling of events soon (they have said they will).

Marketers who 'nailed' their profile...according to LinkedIn!

In this article from the LinkedIn marketing blog they cover three areas of profiles with examples of what they consider to be best in class.

• Headlines - all good examples and some good advice
• Summary (which is actually called 'About'!) - Whilst the advice is generally good here and some of the examples have strong points, all 3 profiles featured are describing the person in the 3rd party! In a world where authenticity is more important than ever, this is a grave mistake!
• Featured. All good examples and the advice is sound.

Authenticity becomes more important amid AI advancements.

With the meteoric rise of chat GPT and artificial intelligence becoming more and more prevalent on this platform, it seems clear to me that authenticity is more important than ever.

If things carry on the way they are currently, I suspect that AI will be so good by the end of this year that it will be assumed that every profile is written by a robot and that every message received on LinkedIn is also artificially generated.

This won't be true but it's the perception that's important.

If everyone that reads our profile, direct messages or even articles assumes that it has been written artificially then we have a problem. People want to get a 'feel' for the person behind the profile and they will soon start to believe that this is no longer possible (it definitely is now).

We can combat this by using tools currently available and other tools that I suspect Linkedin will make available to differentiate our profiles from those constructed artificially.

• Make sure you have a profile video, this is no longer a 'would be nice' but essential.
• Make a video of you talking to camera explaining more about your background and what you do (in effect what would normally be in your about section) and put this in your featured section.
• If you must write your story be very careful to craft it in a way that will be clearly distinguishable from something artificially written.
• We will still need text in our profiles but this will merely be for the benefit of search, keywords and the algorithm.
• Tell your career story by adding videos in the media section of each position in your experience section (see my profile as an example).
• Make the vast majority of your direct messages either voice or video messages.
• Jump on a Zoom or Teams call as early as possible in your interaction with a potential customer, candidate, or employer.

Post of the week

Well it's clearly the hottest topic around so it seems appropriate to feature a post about ChatGPT.

Ryan has done a great job here by combining a topical subject with an opportunity to demonstrate his own skills (copy writing).

It's also a really well constructed document post.

Okay that is it for this week, please continue to let me know if you see anything different or new on LinkedIn. I won't always feature it but unless I know about it I can't assess whether it's something that we should all know about or not!