Monthly Archives: December 2024

work

My GenAI Toolkit: Lessons from 2024

This past week, OpenAI announced o3; all reports suggest they’ve achieved some form of AGI. I’m struggling to wrap my head around this because AGI always seemed like a distant future concept, not something that’s here now. But let’s set that aside for a moment and examine how AI has shaped my 2024.

My primary use for Generative AI (GenAI) this year has been in communications. Despite considering myself a good communicator, having English as my second language sometimes leaves me fumbling for the right words. Grammarly helps, but GenAI takes it to another level. Here’s how I use it:

I start by crafting my messages as I always have, aiming for clarity and audience appropriateness. Then, I turn to ChatGPT, which is fine-tuned with my custom instructions and memories of prior interactions, to enhance my prose. The result? My words, but amplified – like my brain on steroids. Sometimes, I need to tweak the output, but it’s usually spot-on.

For work, ChatGPT is also my go-to for creating user stories for my agile backlog. With a prompt I’ve perfected and a keyboard shortcut, I can turn a few bullet points into a nearly complete user story in seconds. I might remove some overly ambitious acceptance criteria, but it’s mostly ready to go.

When I need to craft a precise prompt for a unique task, I turn to Claude Sonnet through Perplexity. Sonnet excels at understanding my goals and generating detailed prompts that I can then use with other AI tools. For one-off tasks outside my daily routine, I compare outputs from various AIs, picking the best elements from each after generating the prompt.

Shifting gears to another aspect of my work, coding has not been a major part of my job this year, accounting for less than 10% of my activities. However, I’ve relied on Sonnet for both personal projects and quick Proofs of Concept (PoCs). I also used Sonnet for code review to ensure quality before sending pull requests.

Now, let’s talk about Perplexity. It has become my go-to search engine, especially for troubleshooting. It combines the base-model AI knowledge with real-time search results, providing insights far beyond what Google can offer. As a pro subscriber, I can access multiple models but stick with Sonnet. Perplexity gives me access to the model since I don’t have a Claude subscription.

Lastly, there’s Grok. As a premium subscriber on X, I use Grok-2 for its superior image generation capabilities – four high-quality images at once, and fast. The recent integration of Grok into X’s interface is a game-changer for context understanding on social media. Plus, Grok’s ability to pull from X’s vast data pool makes it an excellent tool for quick updates on trending topics. And, for those times when I need an unfiltered, straightforward answer, Grok delivers without the annoying woke agenda that sometimes colours other AI outputs.

At the end of the year, the cost of all these AI tools isn’t trivial, but the productivity and work quality boost justifies it. If I had to choose just one for budget reasons, I’d pick Grok. It’s cost-effective, and given its rapid development pace, I believe it will soon close the gap with other models.

To drive home my point about Grok’s versatility, I’ve used it to refine this very post you’re reading now. Grok’s assistance in restructuring, enhancing readability, and generating this closing paragraph demonstrates its capability as a comprehensive tool for content creation and editing. It took more manual updates than ChatGPT usually does, but it’s still good. I hope this insight helps if you’re still figuring out how best to leverage GenAI in the coming year.

work

Building a Cohesive and Recognized Team

Our team of about seventy people is a relatively small part of our company, which has over three thousand employees. While many of our engineers are well-known among peers in software engineering or customer support, there are simply too many of us—and them—to remember who belongs to which group and what everyone does.

To address this, we asked all our engineers to add a common tag to the end of their profile names on Zoom—e.g., (TEAM). This small change had an outsized impact.

A Common Identity

We are a global team spanning multiple time zones and countries. While our software engineering peers in Poland might not personally know our Australian engineers, the (TEAM) tag immediately signals our presence. It establishes our identity and reminds others that we are part of a cohesive group.

In large all-hands meetings with hundreds of participants, the (TEAM) tag makes us stand out. Even if other teams have greater numbers, their lack of alignment in presenting themselves visually means we often appear more united. The effect is even more striking in smaller meetings. When eight or ten of us join a call with two dozen attendees, our presence is unmistakable. This has led project managers and account executives to comment on—and thank us for—our “massive” presence.

Building a Reputation

Our team is relatively new, created after a reorganization to enhance operational efficiency and reliability. Establishing credibility is crucial, and I firmly believe that consistently showing up is the first step in building a strong reputation.

The (TEAM) tag helps cement this image. Over time, colleagues begin to associate our engineers with reliability and support, creating a lasting impression that extends to the entire team. This subliminal connection—that (TEAM) members are dependable and always ready to help—lays the foundation for trust.

Of course, reputation requires more than just showing up. Our engineers strive to embody a helpful, collegial attitude, always willing to go the extra mile. Without this, the effect could backfire.

Attention to Detail Matters

Details are important. Just as uniforms in the military or sports convey identity and professionalism, our (TEAM) tag serves as a quick visual identifier. However, maintaining consistency in the tag format was a challenge. Despite clear instructions, we initially saw a variety of implementations: (TEAM), (Team), ( TEAM ), and even plain TEAM.

As an SRE team, this inconsistency reminded me of code reviews. Just as we enforce standards for variable names, code formatting, and organization, we should hold our visible identifiers to the same level of rigor. Allowing incorrect formatting, especially in something as visible as a Zoom tag, sends the wrong message. It undermines the professionalism and credibility we aim to project.

Attention to detail is about more than aesthetics; it communicates that we care about doing things right. As the adage goes, “How you do anything is how you do everything.”

Conclusion

What started as a simple effort to ensure visibility during meetings evolved into something far more impactful. The (TEAM) tag not only fosters a sense of unity but also helps build our reputation as a reliable, professional, and detail-oriented group. It’s a small detail with a big message: we show up, we care, and we deliver.