Nels Lindahl — Functional Journal

A weblog created by Dr. Nels Lindahl featuring writings and thoughts…

Category: Software

  • Day 2 working with the OpenAI Codex Beta

    Earlier this morning I did some work with the OBS application to record my efforts to mess around with the OpenAI Codex Beta. For the most part I have been working in the Codex JavaScript Sandbox asking the API to return things related to fractals and a bit of searching out some encryption related elements. The lossless video that was recorded produced about 30 gigabytes of AVI video file for five minutes of recording. That is an epic amount of data for such a short video. I’m still not entirely sure why the massive difference exists between indistinguishable quality and lossless. It really is about a 10x difference in file size between the two recording methods. Uploading that 5 minute video to YouTube took about 2 hours and the crunching that is about to happen in the background over on the YouTube side of the house will be epic. I’m going to record a few more little videos this weekend and it’s going to generate a huge amount of video data.

  • Day 1 working with the OpenAI Codex Beta

    Welcome to day 1 of my efforts working with the OpenAI Codex Beta.

    I’m starting out logged into https://beta.openai.com/dashboard

    The first thing I noticed is that my interface is a little different from what I watched on Machine Learning Street Talk https://www.youtube.com/watch?v=1CG_I3vMHn4&t

    Tim and Yannic are working with the Codex JavaScript Sandbox. My beta dashboard only takes me to the Playground area where you can experiment with the API. 

    Well a couple quick Google searches on that one and it was user error on my part that kept me away from the sandbox. I did not know enough to go directly to the sandbox: https://beta.openai.com/codex-javascript-sandbox

    I downloaded a copy of “The Declaration of Independence” and saved it as a PDF on my desktop. My big plan for tonight is to make an encryption application and have it encrypt that file from my desktop. It’s not a super ambitious plan, but I think it is a good place to start.

  • Waking up before my alarm

    Adventures abound in the world of coding today. So many new things are being tried and mixed up together in coding projects. A few simple searches on GitHub will quickly take you to all sorts of things people are working on as major projects and things people are just tinkering with for fun and adventure. At the moment, I’m sitting around wondering about the myriad of machine learning use cases in general business execution. A lot of the examples are related to online transactions and how to make that process more efficient or improve suggestions. The rest of the examples that came to mind right now are sorting related. That is probably an artifact of how early it is in the morning at the moment. Today was one of those days where I woke up before my alarm clock and started writing. 

    Things are moving along outside here before everyone is awake. We have a few rabbits outside and a squirrel. None of those creatures care that I’m sitting here writing at my desk. Not one of them is even marginally concerned about my writing activities. That is probably for the best. Here in an hour or so the dog will want outside in the backyard. Not only do the creatures in the yard remain unconcerned about my writing, but also the dog will not care at all about the writing that is occurring. I imagine that the dog considers my sitting in this chair and writing or working much in the same way it naps throughout the day. This type of writing is a type of mental reflection mixed with exercise. Simply sitting down and writing a stream of consciousness requires a certain amount of discipline. 

    Each day I sit down and open a word processing document and begin writing whatever comes to mind at the start of the day. That is my current writing routine. It helps get things going as the day begins. After waking up in the morning it takes a few minutes to sort of boot up and get going at full speed. Within those first few minutes of the day sitting down and starting to write seems to be working. It does focus my thoughts on something. The problem with it is that the something that receives focus is entirely decided at that moment. Perhaps that is also a good thing as well. It means that just about anything that could tumble into the forefront of my thoughts could receive my attention at the start of the day. Right now the two shots of espresso I consumed at the start of all of this are truly starting to kick in and provide a bit of a boost. Perhaps that will sharpen my writing from this point forward during this writing session. It is entirely possible that the prose will remain the same quality.

    Writing for another 45 minutes remains a strong possibility assuming that no interruptions occur. Given that many minutes I could switch over and keep working on my GPT-2 model coding project or really anything else that deserves attention. Deciding what to do next is always the key and most important element in the things that happen each day. Making a commitment to doing the things necessary to make something extraordinary happen is about taking action. Very few truly extraordinary things are created from inaction. That is the nexus of the choices that we make about taking action to strive forward or the lethargic descent into the madness of inaction. After taking some time to reflect on the feeling that sums up quarantine the best it would be that feeling of inaction. It is strangely a feeling that is mixed with a will to want to do something, but not knowing exactly what action would be helpful. I’m not sure my vocabulary includes a word for inaction caused by the inability to see a plausible path forward.