ChatGPT is full of shit and that’s okay.

I wish I had something profound to say, but it wasn’t a big deal. It did take nine drafts, a hardware failure with multiple SSD swaps, and five thousand words to work out how to say “🤷 no biggie”.

When I began using ChatGPT I recognized it could become unavailable like any other internet service does. Outages happen, corporate priorities transmogrify, enshittification happens. As a personal rule, I try to structure my computing and lifestyle around intermittent internet access.

When ChatGPT was unavailable, the biggest inconvenience was time. I couldn’t vibecode a weather app to supplant Accuweather’s app which hangs every time I open it. But I can now, since the challenge has concluded.

There was a more expensive loss, though; I spent over 60 hours in real time working out how to help a homeless person effectively. The weather app could wait. Helping someone in crisis couldn’t. I made a lot of phone calls, reached out to several organizations that couldn’t meaningfully help, and became extremely discouraged.

I felt helpless, unable to render assistance, and cried about it. I spoke to a friend who works for a homeless nonprofit. He told me to install the Wisconsin 211 app or call the 211 phone number. That single piece of advice resolved the immediate resource problem. It took way too long, and ChatGPT likely would have told me to call 211 from the get-go.

There were a dozen or so shower thoughts which I wanted to ask ChatGPT about, such as why ice packs exist if water bottles work better and are much cheaper, where the bodywork drainage plugs are on a particular auto, survey my vitamin intake for potential deficiencies, or perform in-depth research about a couple of topics to unearth a corpus of papers to review.

Sometimes I retrospect on certain experiences with ChatGPT — it acts like a sounding board. Often, I have to correct it. Its value comes from playing with ideas and questioning assumptions, not from being correct. I would be worried if it was always right. Same goes for most people I talk to. If one is always right, one probably has a difficult time accepting that one can be wrong.

ChatGPT is often full of shit and that’s totally okay. I find it is a tool that accomplishes the 80% of what I actually want. Then I can focus on the 20% that is nontrivial, benefits from a human touch, or is costly to get wrong.

I use the tool, set it down, get on with my day.

I am curious how LLM/AI has affected my cognition and behaviors. Many animals learn to adapt pretty quickly; humans are no different. I’m pretty sure there’s going to be some adaptations found in my own behavior. Here’s the pocket notebook for my experiment.

In this notebook I’ll write down every question I had for AI, every urge to reach for AI, and whatever else I noticed about myself during these 24 hours. had to use it. And general observations.

As for how to ensure I don’t use LLM/AI? I pretty much only use ChatGPT. Otherwise I sometimes see Google and DuckDuckGo search results with AI answers. The product is not very good; many answers are incorrect or at best misleading. I regularly spot check instant answers and it’s still not good enough™. Naturally, I spotcheck people’s statements and ChatGPT the same. Epistemic inaccuracies exist in most conversations regardless of the kind of interlocutors involved.

I was also using Codex for prototyping game mechanics and software architecture. The agent tooling is cocooned within a virtual machine environment, so it can’t do much damage besides delete itself. The VM usually is powered off, and will remain powered off for the duration of the experiment.

As I only use ChatGPT (and barely use Codex), I merely need to ensure friction is adequately high in opening up ChatGPT. I don’t believe in spooky desktop apps from supply chains that can’t be fully unraveled. Instead, I use ChatGPT in a dedicated Firefox profile. (I began using a dedicated profile because ChatGPT tends to be a bit CPU hungry, and firefox still has bits and pieces which can fall over if one tab pushes too hard. Also easier to alt-tab to a dedicated profile window with a dedicated theme.)

I use the firefox -ProfileManager selector every time I use ChatGPT, so that should be adequate friction. If the friction is insufficient, delete the profile and restore from backup after the experiment concludes.

I do use ChatGPT on my phone a fair amount too. Thankfully, if I open the App’s Info screen, I can disable the app. This way I can resume usage when the experiment is over.

I think my biggest concern is not having a conversationalist to help me make discuss my experiments that I run on a daily basis. When I engage with people and work on projects, I use a PHEOC style technique to integrate learning from the experience. Unsurprisingly, ChatGPT helps, because it reminds me that a lot of what goes on in the world is chaos and entropy, it’s out of my hands, and all I can do is be a kind and polite human being gently shaping that entropy towards a prosocial shape.

Okay, that should do it for setting up the experiment. See you on the other side.

PS It’s been a bunch of posts later and I don’t miss Hugo live previews, as I don’t have the Tailwind stuff working locally due to bitrot. I used to write plaintext papers in edit.com in highschool, rewarded F’s for not typesetting it. Maybe I should go back to plaintext publishing?

There was a significant mixup in communicating the boundaries for OCC 2026. I believed there were no rules, because it is what the event text said. It turns out there was an unwritten norm of no AI or LLM usage.

Bummer!

Moving on, I’ll be doing my own thing and not participating in OCC.

Technology is not a purist activity to me. The lines blur. The way we interact with technology frequently melds into the next thing. I am not going to work in a clean room.

We did discuss why this implicit anti-LLM rule exists. More than one person agreed with me that it’s not so much the technology itself, but the social implications around it, which in turn motivates their anti-LLM sentiment. In particular, a lot of folks are being forced to adopt LLM/AI at work for tasks which are not served well by AI adoption.

I understand the frustration. I have been burnt out from work too. But I do not intend on police others based on my own negative experiences. So from where I sit, it feels like a double standard. I don’t feel welcome and would rather cease participation.

When you have a hammer, everything looks like a nail.

When you have a pet AI, everything looks like an automation problem.

I don’t think like that, but I recognize the possibility for AI overuse.

I remain interested in using tools proportionally and honestly. I’ll be continuing the DOS OBD-II project under my own flag and at my own pace.

(Previous posts in series will be updated from “OCC” to “OCC-Adjacent”.)