Aaron Alexander

Recent Articles

AI concept art

How Autonomous AI Agents Leverage Text Completion Capabilities

This is the fourth post in a series that looks at how autonomous agents use generative AI models. Introduction The previous post showed how programmatic interactions with Open AI’s language models function. In this post, we’ll look at how two different autonomous agents (BabyAGI and Auto-GPT) leverage these capabilities. Agents like these provide a way […]
Read Full Post

Chatting With A LLM – Using the Open AI APIs

This is the third post in a series that looks at how autonomous agents use generative AI models. Introduction The previous post discussed how the text completion and chat completion capabilities work generally. It also showed some examples of prompts and responses. In this post, we’ll see how to use Open AI’s API to perform […]
Read Full Post
Robot at a computer

Probabilistic Chatting – How Text Completions and Chat Completions Work Behind the Scenes

This is the second post in a series that looks at how autonomous agents use generative AI models. Introduction The previous post introduced transformers and how they impacted recent natural language processing (NLP) developments. In this post, we’ll take a look at how this sort of transformer model works with completion and chat completion interactions. […]
Read Full Post

The Rise of Transformers – An Introduction to Transformers and LLMs

This is the first post in a series that looks at how autonomous agents use generative AI models. Introduction The past few years have included rapid advancements in the field of artificial intelligence (AI). These advancements are particularly demonstrable in the natural language processing (NLP) domain. Newer transformer based models have demonstrated remarkable capabilities in […]
Read Full Post

Suddenly Remote?

I shared some thoughts with my team last week as we were thinking through what all-remote would look like for us. Now that we are in an all-remote stance (as are an increasing number of companies), those thoughts are more broadly applicable. The tips below are things that have helped me work effectively in the […]
Read Full Post

4 Ways We Attract Great Interns

Finding top-notch people (engineers, designers, etc.) to work at SEP is a key thing we focus on each year. As part of finding and attracting great interns, it’s important to have a clear idea of what your company has to offer. Students will interact with lots of companies, often in quick succession. Knowing what you […]
Read Full Post

5 Products Built During Our Hackathon That We Actually Used

When we run company hackathons we end up with quite a variety of ideas. The teams working on these projects always get something out of them regardless of whether the projects continue on past the weekend. We do have some projects that go further than fun over the weekend. These are the products that we […]
Read Full Post

How We Run Company Hackathons

We’ve been running hackathons at SEP since 2011. Over the years we’ve experimented with the setup. It’s ranged from actual product pitches to technology explorations (and everything in between). Recent hackathons have settled into a pattern that works well for us. That pattern includes: Pitches Q & A Form teams Build Demos Our hackathons run […]
Read Full Post

Automatically keeping Git identities distinct between accounts

I’ve ended up with multiple GitHub identities. One for personal use, another for SEP use, and still more for many of our clients. Leaning on Git conditional includes, and a bit of manual work upfront, my GitHub identities can be “automatically” kept distinct. Like many people, I’ve setup a global Git configuration for my name […]
Read Full Post