Month: October 2023

Communicate to Collaborate

One of the most difficult aspects of any job is working with someone who
communicates through conflict rather than collaboration. They communicate in absolute terms and it may feel that there is no room for discussion or cooperation. This frequently occurs in the dissemination of policy changes from a person in a position of authority or a peer when providing feedback.

The immediate reaction of the recipient of this message is to become defensive and resist. They recipient may feel resentful, frustrated, and respond by lashing out or countering the message they are receiving. The conversation becomes a conflict instead of a collaboration.

Working through a conflict is much more challenging than having a collaborative discussion. Conflict cannot always be avoided, but it should never be the preferred path.

Communication through collaboration will be a much more successful path. This requires more thinking, emotional intelligence, and tact from both parties. The conversation will create a shared understanding as the parties seek to understand each other’s perspective. A resolution will be reached only through this shared understanding. Otherwise, resentment lingers and conflict surfaces.

When communicating at work, or anywhere for that matter, ask yourself how you are working to collaborate and try to actively avoid generating an unnecessary conflict.

Prompt engineering as introduction to AI

I had only read articles and listened to a few podcasts about AI, ChatGPT, and other machine-learning algorithms prior to this past month. I was able to get hands-on experience with ChatGPT 4 while participating in an AI hackathon for work.

Our hackathon idea focused on using ChatGPT to transform a multi-input form entry into a single text input. We would use ChatGPT to extract context and relationships from the text and automatically enter these fields and create relationships in the system for the user.

I was skeptical of ChatGPT’s ability to extract this information. I thought that it would be able to categorize the input, but I was unsure it could extract all the required metadata that was normally tediously entered by the user. I was blown away by what it was able to understand.

ChatGPT operates in a conversational manner. The application provides a prompt on how ChatGPT should respond when given an input. This includes a system message instructing ChatGPT on how it should operate. This is followed by pairs of example inputs and outputs where the input is supplied by the user and the output by the ChatGPT “assistant”. These examples are used to instruct ChatGPT what sort of output is expected for a given input.

Programming typically involves writing high-level code in a procedural way to get the computer to produce a desired result. There are very clear rules on what this code should look like and what it can do.

Prompt engineering is an open-ended narrative. Producing these prompts was a back-and-forth exercise in trying to use prose to instruct a computer how to operate. I had no experience in using ChatGPT so I began playing with different writing formats, styles, and commands to get the desired output. It just felt… fun.

With surprisingly little effort, ChatGPT was able to recognize dates and times, extract the names of people and businesses, infer relationships from the context of sentences, and connect a location to an explicit timezone. It was truly impressive. The majority of the development time spent on our project was on application code calling ChatGPT and taking actions based upon its results. It was impressive.

I left the hackathon with a concrete understanding of a use case that could directly benefit our users. I saw what other teams built for their projects and other ways it could be utilized in different contexts. I feel excited that it can be used to actually help people and confident in my ability to successfully leverage AI.

We plan to share our project results as a way to show what ChatGPT is capable of and hopefully spark some ideas for other potential uses in the organization. Maybe it will get picked up as a feature to be implemented soon!

Step outside your comfort zone

Change is scary. At least, that is what my brain thinks when I think about change. When pushed too far outside my comfort zone I become anxious. Self-doubt creeps in and I tell myself I should not have done something differently or tried something new. My brain lies. Usually, anyway.

This past month I had the opportunity to participate in a AI hackathon for work in Budapest. I signed up without hesitation. AI technology has seemingly exploded within the past six months and has become accessible to those with a basic understanding of it as I had. This would be a great opportunity to learn about AI and learn directly from colleagues using it in production. In addition, my manager is in Budapest and we collaborate with folks in that office so it would be great to connect and network with them.

As the date approached, that resistance to change began to set in:

  • Worry about traveling to a new country where I did not speak the language.
  • Fear that I was not good enough to fit in and participate.
  • Concern that we would not be able to deliver our project and I would be exposed as an imposter.

I was also excited. I was being joined by great co-workers. I wanted to learn more about AI after seeing its applications that truly astounded me. I wanted to travel somewhere that I did not know the language. I wanted to try and build something, even if it was bad or I failed.

My brain lies.

I had a fantastic time. I met colleagues and was able to connect with them in ways that would not be possible strictly through video. I had fun exploring with teammates and will have fond memories of spending time together on this trip. We stumbled at the start of our application building but worked together and had fun building something that actually worked! We learned and grew. Even if we had failed it would have been a great learning experience.

Step outside your comfort zone and try new things every now and again. That is the way we learn and grow. The end result is usually a better you, whether or not it worked out exactly the way you planned.