A burn so severe, so long-lasting, that he no longer has to pay to heat his home.

I use a system prompt that forces it to ask a question if there are options or if it has to make assumptions

I’m kind of amazed that even works. I’ll have to try that. Then again, I’ve asked ChatGPT to “respond to all prompts like a Magic 8-ball” and it knocked it out of the park.

so I start a new chat frequently.

I do this as well, and totally forgot to mention it. Yes, I keep the context small and fresh so that prior conversations (and hallucinations) can’t poison new dialogues.

I also will do the same prompts on two models from different providers at the same time and cross reference the idiots to see if they are lying to me.

Oooh… straight to my toolbox with that one. Cheers.

That’s been my biggest problem with the current state of affairs. It’s now easier to research newer tech through an LLM than it is to play search-result-wack-a-mole, on the off chance that what you need is on a forum that’s not Discord. At least an AI can mostly make sense of vendor docs and extrapolate a bit from there. That said, I don’t like it.

When writing code, I don’t let AI do the heavy lifting. Instead, I use it to push back the fog of war on tech I’m trying to master. At the same time, keep the dialogue to a space where I can verify what it’s giving me.

1. Never ask leading questions. Every token you add to the conversation matters, so phrase your query in a way that forces the AI to connect the dots for you
2. Don’t ask for deep reasoning and inference. It’s not built for this, and it will bullshit/hallucinate if you push it to do so.
3. Ask for live hyperlinks so it’s easier to fact-check.
4. Ask for code samples, algorithms, or snippets to do discrete tasks that you can easily follow.
5. Ask for A/B comparisons between one stack you know by heart, and the other you’re exploring.
6. It will screw this up, eventually. Report hallucinations back to the conversation.

About 20% of the time, it’ll suggest things that are entirely plausible and probably should exist, but don’t. Some platforms and APIs really do have barn-door-sized holes in them and it’s staggering how rapidly AI reports a false positive in these spaces. It’s almost as if the whole ML training stratagem assumes a kind of uniformity across the training set, on all axes, that leads to this flavor of hallucination. In any event, it’s been helpful to know this is where it’s most likely to trip up.

Edit: an example of one such API hole is when I asked ChatGPT for information about doing specific things in Datastar. This is kind of a curveball since there’s not a huge amount online about it. It first hallucinated an attribute namespace prefix of data-star- which is incorrect (it uses data- instead). It also dreamed up a JavaScript-callable API parked on a non-existent Datastar. object. Both of those concepts conform strongly to the broader world of browser-extending APIs, would be incredibly useful, and are things you might expect to be there in the first place.

A garlic sauce containment breech is nothing to sneeze at. Entire living rooms have been rendered uninhabitable by such events.

I think that’s closer to 500-750ml. I wonder what the 250ml amount was intended for? Are people dunking their crab rangoons in this stuff?

The answer is: binary, sometimes with electrical switches.

As late as the very early 1980’s, the PDP-11 could be started by entering a small bootstrap program into memory, using the machine’s front panel:

You toggle the switches to make the binary pattern you want at a specific location in RAM, then hit another button to store it. Repeat until the bootstrap is in RAM, and then press start to run the program from that first address. Said start address is always some hardwired starting location.

And that’s a LATE example. Earlier (programmable) systems had other mechanisms for hard-wired or manual input like this. Go back far enough and you have systems that are so fixed-function in nature that it’s just wired to do one specific job.

Granted, nobody needs a conspiracy or invisible hand to create problems like this.

That said, it’s far easier to look for weak points to exploit for political means, than build a new movement from whole cloth. In the US, ideological divisions, wedge topics, racism, and even the ghost of the Civil War, have all been used to sow division for various means.

Industrial: The world is broken and has been for a while so let’s go to the abandoned husk of the inner city, throw a party, and make insane music before it crashes down around our ears.

Eh, gimme something else.

Yeah, that’s pretty awful. The pandemic taught us all that enough people are gross like that.

At this point, I just assume that every airport is packed to the gills with coronavirus. I mask up, avoid eating with my hands, try not to eat much at all, and wash thoroughly. That said, I ate at a sit-down restaruant at O’hare this summer and immediately caught it anyway; my flight was delayed and i was ravenous.

No kidding. Every time I fly I wind up on the same flight with a bunch of people that hit up an all-you-can-eat chili buffet the night before. They proudly let the entire cabin know this the very instant we hit cruising altitude.

The only upside here is that not even first-class is safe. I really feel bad for the flight attendants.

It’s worth mentioning that the flatogenic index of that kind of eating is off the chart. If anyone reading this has a diet like that please, for the love of everything good in this world, get a job that is outdoors.

What really breaks my brain is that the pigment responsible for this purple hue are called anthocyanins. It literally has a root-word for blue in the name, even though that’s not the only color it can make.

Thanks for the rabbit hole. Here’s a youtube video of that screencap.

https://www.youtube.com/watch?v=iJerbSVIBEQ

And here’s a (VHS quality) archive of the whole show. It includes all the advertisments too, so it’s quite the time-capsule:

https://archive.org/details/dinnerandamovierockyiii

It’s even better worse if you hear it at a dead mall, with hardly anyone around and almost no open stores.

Oh wow, that is so me. That had better be under… yep, ADHD… yeah, that’s in the right place.

It’s worse when this triggers life-long anxiety about missing future appointments.

Worse still is when you show up a week early by accident, because you had it wrong in the other direction.

Every time.

I have left this as an exercise for the reader.

Fixed: