Image-to-Prompt in Midjourney

booleanstrings Boolean Leave a Comment

Midjourney has just released an amazing feature, invoked by the command /describe. You can upload an image and get four sample prompts to draw in Midjourney. This is “image-to-text” that creates only remote likeness to the subject. (I suppose photos of famous people and such may be better replicated). Instead, it creates four fantasies. Of course, you can edit the prompts as you wish.

Here is an example. I uploaded the above plain “Boolean” image, then ran the output through Midjourney. The results are interesting:

This feature adds a new layer of creativity. It also reveals some prompt secrets.

See (and hopefully like) my AI art at https://www.facebook.com/aibraingain/.

Google’s Bard: an Immature AI

booleanstrings Boolean Leave a Comment

I appreciate the “code red” that Google had experienced seeing ChatGPT success. However, Bard, Google’s response to AI, is quite underwhelming. Google should have given it time and effort to mature, I think.

The web is full of hilarious dialogs with Bard like

ChatGPT and Bing Chat seem to know more about Google than (its own) Bart. This is ridiculous!

At the same time, I do not feel like there is a solution of LLMs combined with web search yet. Due to Bing Chat’s hallucinations, I mostly Google, not Bing Chat, for recent news and facts. For text editing, research questions, anything language, my choice is ChatGPT and Grammarly. That said, Bing Chat is improving.

Exiting times!

The image above is made with Midjourney; I generate prompts with ChatGPT. Please see my portfolio at the Facebook page The Prompter.

 

Softly, Softly, Catchee Monkey. About Taming Bing

booleanstrings Boolean Leave a Comment


[ image generated with #midjourney. I do not mean that Bing is like a monkey, it is just an expression. See my portfolio on FB. ]

As we have all experienced, Bing Chat is “stubborn” and “lazy” (so is ChatGPT). After Bing’s volatile and “emotional” first day, it was told to say “no” more often than not.

If Bing responds to you with its infamous “I am an AI model” or any other objection, do not believe it until you have tried. There are things to do:

  1. Start a new chat and repeat the prompt – you might get lucky.
  2. Rephrase the prompt. (Some say saying “please” also helps!)
  3. Slowly talk Bing into doing the task it had rejected by taking small steps.

Here is an example of #3. I got a test list of LinkedIn profile URLs and asked Bing to generate a table based on them. It refused, telling me it has no access to the pages – only to search results and its training data.

I repeated the request with only one URL and got the beginning of the table – which Bing gladly generated. Then I asked to add one more URL, three more, and it worked. The result is scraped profiles for a list of LinkedIn URLs, where, unlike with SalesQL (which is a great contact finder and scraper), you do not need to log in.

I do not know how scalable this is, but perhaps we can “softly” teach Bing to create massive scrapes of profile lists. That allows to sort and filter by values unavailable on LinkedIn.

Here is another application: I have a list of candidates and want to know which ones work at midsize companies. I feed Bing a list of companies, starting with one, and increasing the number of fields by which I want to sort. Bing gets drawn into the task.

Bing Chat and ChatGPT plug-ins are promising aids in scraping public pages and even cross-referencing information on different sites.

As a reminder, registration is open for

Six-Day Sourcing Bootcamp with Irina Shamaeva,

where I will cover AI in recruitment as well all tools, techniques, and strategies relevant to sourcing. April 4-April 13, 2023. Seating is limited.

What March 2023 participants have said:

“Just wow! Very fortunate to learn from you. Thank you!”
“Having followed Irina for several years, it was very refreshing to be overwhelmed by her knowledge and the information she shared. Now I have to complete all the homework.”
“Irina you have an amazing knowledge ! I am impressed by seeing what you do in sourcing. Many thanks for the course!”
“I have been passioned about recruitment , have been working for past 14 years in that filed but your course showed me that I have gaps in sourcing and still much to learn from you and others! Homework is to be done but I need to be still studying your materials!”

GPT-4: Game-Changer for Image-to-Text?

booleanstrings Boolean 3 Comments

GPT-4 tells fewer lies. For example, it correctly lists Google search operators. What I find most interesting though at the first glance is its exceptional ability to interpret images based on URLs. There is no restriction for the creation time. I gave it the image above and it produced a perfect output:

I would do face recognition, too, and tell you the person’s bio – try it on someone’s photo.

OK, it was wishful thinking for now! After a few colleagues’ comments and a few more tests, I realize that it is hallucinating based on the image URL. So what does multi-modal mean?

P.S. Please follow my Midjourney AI Art at my new page The Prompter. I use a ChatGPT-based prompt generator. 🙂

Defeat Continuous Scrolling

booleanstrings Boolean 2 Comments

Google has been rolling out continuous scrolling, and it’s a challenge. Seeing all of your results now requires a lot of scrolling down and pressing the “more results” button.

There is a preference, but it does not influence Google’s behavior (at least for me):

The change is unfortunate. Chrome extensions and other tools will break over the scrolling format.

However, there is a workaround. Add &start=<any number> to the end of your search URL, and the familiar view with numbered pages comes back. Following the link, you will arrive at the second page and then all tools, including Instant Data Scraper, will behave again.

So, to view or collect all results:

  1. Get results from the first page
  2. Use &start=1 to get to the second and following pages.

Note that the “include omitted results” option is now hard to reach:

Therefore, remember to add &filter=0 to your search URL to get more results from the same sites.

Join us at the renewed Boolean Strings Basics & Beyond on March 1-2, 2023. We will cover principles that are staying and new developments that change the best ways to Google, like the one above, as well as touch on Google vs. ChatGPT competition.

As a reminder, I am holding a Six-Day Sourcing Bootcamp with Irina Shamaeva March 7-16. I will cover all things sourcing in this course. It is filling up, so if you are interested, I recommend signing up.

Bye, #ChatGPT DAN!

booleanstrings Boolean Leave a Comment

There is no need for “DAN” Do Anything Now jailbreaking prompts to try and access the web anymore. The New Bing Chat has changed that. 
The new Bing does not look like “the search engine Bing combined with ChatGPT”  – it is “Bing Chat,”
ChatGPT with web access
(in a different tab even). That is excellent news!
Here is an example of what you can do as soon as you get access to the new Bing.  Prompt:
Be cautious, though! ChatGPT always starts with minimal effort. Tell Bing Chat to be thorough. Tell it to digest the pages fully; otherwise, it may begin to hallucinate. There are still potential limitations that we will discover by practicing.
What are your experiences with the new Bing?

ChatGPT Will Not Replace You If You Embrace It

booleanstrings Boolean Leave a Comment

My recent LinkedIn poll, “Recruiters: are you already using #ChatGPT in your work to write emails to prospects and other content?” shows an impressive rate of acceptance and interest in ChatGPT.

Our Facebook group ChatGPT, Artificial Intelligence, Prompts, Insights for Recruitment amassed 5.6K+ members in no time; I have never seen such growth. The LinkedIn group with the same name is exploding as well.

Attitudes vary a lot, though. Answering “What is your interest in ChatGPT?” someone joining the FB group said, “Know thine enemy.” (lol)

Some skepticism arises from unimpressive initial uses.

  • If you tried ChatGPT and it produced a generic, mediocre piece of writing, you may have voted “It is not good enough” in the poll. But rewriting your prompt and giving it additional direction will help!
  • ChatGPT sometimes states the wrong facts. It is not a good reason to stay away from it! But remember to verify its output.

On the other hand, some enthusiasts believe they will now automate any writing. Or they worry about their jobs. Not so fast! If you spend at least a few hours with ChatGPT, you will learn that getting the desirable, well-written piece requires a lot of effort, guesswork, testing, and (yes) Googling. Just as there are no useful Boolean Builders, there is a limit to lists of universal ChatGPT recipes anyone can create. Using ChatGPT is more of “know-how.”

We have pushed ChatGPT’s tires a bit, and I will be sharing what I have learned in a webinar. The proceeds will go to a good cause.

Pease join me at a 90-minute webinar Revolutionizing Recruitment with ChatGPT and AI (Ukraine Benefit) on Wednesday, February 15th! Some of the topics I will cover are:

  • Introduction to ChatGPT and its capabilities
  • ChatGPT vs. Google
  • How ChatGPT can be used to streamline and enhance various aspects of the recruitment process
    • Research the market
    • Create Boolean Strings
    • Manipulate text data
    • Craft targeted LinkedIn messages and emails to passive candidates
    • Improve your writing
    • Generate interview questions and assessment tests
  • Brainstorm with ChatGPT
  • ChatGPT for everyday use
  • Limitations and how to overcome them
  • Competing landscape
  • Image AI
  • Q&A session

#AI Dialogs

booleanstrings Boolean Leave a Comment

Welcome to the new Artificial Intelligence world that has rapidly arrived!

ChatGPT has no manual! We are equally ignorant at the start. I am OK with it because I am one of those who never read the instructions (lol).

An often-missed so far angle to discuss #ChatGPT is to have a dialog with ChatGPT without an intention to create content (in whatever format). The purpose can be decision-making, brainstorming for work and personal goals, or fast fact-learning, to sound intelligent on a date or at a party with experts or quickly start sourcing.

Same as with any content creation, you can combine conversations with assigning a role to ChatGPT. (You’ve seen those lists.) This adds a new dimension to the output. Here are some excellent recruiting-related A.I. Dialog examples on our new rapidly expanding Facebook Group #ChatGPT, Artificial Intelligence, Prompts, Insights for Recruitment.

As you know, with any request lacking detail, ChatGPT starts with something generic and wordy. Do not be discouraged! You have to be strict and insistent on concrete responses that match your request. I think I am acquiring the skill. 🙂 Observations I will be sharing on the blog, new newsletter, and new group, and eventually, in a class, come from my limited but growing experience.

These bits stand out:

  • A challenge is that ChatGPT has a short memory, so putting together as much info as possible upfront is a good idea.
  • ChatGPT is especially good at generating lists of possible solutions for a problem. You can continue the dialog by exploring each appealing option and making your request more specific based on its suggestions.
  • Do not make your prompts suggestive of an answer. It may lead the Intelligence to try and please you by lying.
  • You can make ChatGPT yours if you start the dialogs, understand what to expect, and share and digest what others have learned. Collective Learning is an essential part of it.

It’s hard not to imagine the tool’s “personality.” I often see ChatGPT as forgetful, lazy, and stubbornly protecting the “gold” it hides somewhere deep.  Think of a fairy tale where a magic phrase opens the treasure guarded by a dragon, and you are the Hero. The tool is an invitation to be creative, imaginative, observant, intuitive, resourceful, and “digitally manipulative” in a good sense. These are keys to the new skill acquisition. And just like swimming or sourcing, learning is inseparable from practice.

Are our jobs in danger? Are you serious? It is a new human craft, and few will master it (as with any art). I read somewhere an analogy that photography did not destroy paintings. A popular tweet reads: A.I. will not replace you. A person using A.I. will.

My colleagues and I are interested due to the possibilities and because we already have the “studying software behavior” curiosity, skills, and experience, after exploring Google’s and LinkedIn’s algorithms in-depth over the years. GPT-3, ChatGPT is quite a new kid on the block! It has trivial stuff on the surface and gold to dig out with new skills.

We are preparing a February webinar to summarize the useful bits of the #AI Revolution for busy Recruiters. Stay tuned by joining the FB communities and following our schedule. Once delivered, classes show up in the Training Library. The 11K+-strong Boolean Strings FB Group will stay on sourcing topics, and AI discussions are channeled to the new group.

P.S. My friends and Facebook followers know that I have also been spending time with Midjourney for image creation for enjoyment.

Sadly, drawing is not of my many talents. But creating unique prompts, some with ChatGPT (a prompt for a prompt!) switches the creativity into the area where I am capable and learning. Think about such possibilities!

I will hopefully figure out a separate channel for my #A.I. galleries. Since I haven’t yet, I want to share a recent creation, a Fruit-Themed Gift:

 

 

You Must Know This if You Use LinkedIn Job Search

booleanstrings Boolean 2 Comments

As part of the dialog with LinkedIn Engineering, I had submitted the strange examples from LinkedIn Job Search Is Haunted.

The reply was unexpected. It parallels Google’s Engineering response on The Behavior of the Quotes (Google Search Report). The similarity is treating keywords in quotes differently, applying less algorithmic interpretation,  and sometimes, generating many more relevant results.

The new insight is inconsistent with LinkedIn Job Search Help.

Read carefully.

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.

When double quotes are used, it looks for exact text matches across various areas of a job. As the double quotes force an exact text match, the system is not as restrictive in filtering out results but rather just returns most that seem to have the quoted phrase in question. That is why putting a common word like “recruiter” in double quotes often returns MORE search results than just recruiter without double quotes.

Keep in mind, we are constantly trying to improve so our strategy today will likely continue to evolve beyond what is described above. These are also not all the details about how search is done but just some of the parts to help understand what you are observing. Your feedback is extremely valued and will help us continue to provide a better experience.

Please continue to provide us your thoughts on how we are doing, what you like about the system and what you do not. Every bit of feedback is a gift to us.

Bottom line, as in Google, use your job-hunting keywords both in quotes and without to find maximum relevant results.

A one-line conclusion:

>> As in Google, in LinkedIn Job Search, use your keywords in quotes and without to cover the ground best. <<

A one-line reason and comment:

>> LinkedIn is “overdoing” semantics (not telling us how or what has changed) <<

If you are a Recruiter using a LinkedIn Premium (Business) account to search for members, please join me for a completely reworked webinar on January 12th, 2023,

LinkedIn Solved.

The two-part class addresses the challenges of sourcing professionals with a Premium account and explains the truth about LinkedIn Search algorithms. It will be helpful for other account holders as well.

 

LinkedIn Premium Engineering Input. No Joy. Workarounds

booleanstrings Boolean 1 Comment

Years ago, I was part of a team, building software for a Mass Spectrometer at Applied Biosystems. I was shocked to learn that the same device was sold for a lower price, with the altered software blocking its advanced capabilities.

Are you a Recruiter with a Premium account? My poll shows that a significant number – about 13% of Recruiters – work with Premium, 134 out of 1,061 votes. Here is what you need to know.

This information is in addition to what I have been sharing – mostly, on LinkedIn Recruiter – on the Boolean Facebook Group since Engineering contacted me in response to a post.

LinkedIn.com Premium People Search – Engineering Input

Feedback on LinkedIn.com Notes by Irina Shamaeva

Not being able to search by phrases from a person’s “about” description. “blending cutting edge technology” not finding David Galley who has the phrase in his About section.

This is an area of search that we continue to optimize to balance between the ability to match everything you want and providing an experience that is fast. With the growth of our member base (800 Million+ now) we made trade-offs between supporting all types of searches possible and the site responding in an acceptable amount of time. This is one such trade-off. We continue to make advances in our underlying technology, so we will take this as feedback for a feature you would like to see improved upon. You will find that searching for some phrases may still work as you think, such as “We have condensed decades of expertise into a series of training courses that will improve your skills, save time” should find David Galley*), it’s just that not all phrases will.

*) It does not.

You will not read this in LinkedIn Help, but we face the truth here. LinkedIn Premium misses keywords in headlines, summaries, and job descriptions in an unpredictable manner. If you source candidates using a Premium account, the above means that you randomly miss excellent prospects. 

How do you work around that?

  • Convince LinkedIn to invest in computer power. (I wish!)
  • Switch to LinkedIn Recruiter ($$$)
  • Switch to Lite or Sales Navigator ($$)
  • Use a system like SeekOut or AmazingHiring ($$)
  • Use LinkedIn aggregating tools like SalesQL or PhantomBuster ($)
  • Understand which search filters work as expected, and adjust your expectations to the current algorithm. 🙂 Search wide, collect results and filter
  • Research deeper to power up your  LinkedIn Boolean
  • Master Google X-Ray; it can do wonders!

The above also means that others may no longer find you by your favorite keywords. (That affects all of us, no matter what account.) Run some test searches and edit your profile to fix that (do not ask me how!)

Please join me for a completely reworked webinar on January 11-12, 2023,

LinkedIn Solved,

addressing the challenges of sourcing talent with a Premium account. We will cover X-Ray in detail. It may be useful for other account holders as well.