Using documents for state helps so much with adding guardrails.

I do wish that ChatGPT had a toggle next to each project file instead of having to delete and reupload to toggle or create separate projects for various combinations of files.

Experience is knowledge of what not to do.

It's the old saying: "$10 for the part, $990 for knowing where to put it"

You get a feel for what works and what doesn't, provided you know the relevant facts. Doing a 10RPS system is completely different than 300RPS. And if the payload is 1kB the problems aren't the same as with the one with a 10MB payload.

And if (when) you're using a cloud environment, which one is cheaper, large data or RPS? It's not always intuitive. We just had our AWS reps do a Tim "The Toolman" Taylor "HUUH?!" when we explained that the way our software works is 95% cheaper to run using S3 as the storage rather than DynamoDB :D

True. I remember myself spending weeks just to figure out what not to do next because I can't afford a redo.

Schrodinger's GPT: it's taking our jobs, while simultaneously only capable of producing useless slop.

That fad is a few hours old.

Now we leave comments about people who think it's just trendy now to say "it's seen as cool to hate AI right now"

I'd say it might be time to talk about putting a pause on incentives to advance non-medical technologies at the moment.

I'm getting up there in age and I'm getting a bit tired of designers moving things around.

It's taking longer to update my muscle memory each time.

I still get pissed off at the Play Store app regularly for moving the search bar AND not focusing keyboard input on it when I click the search icon.

Pretty sure this is why Microsoft acquired Skype.

You're assuming the goals are to improve rather than destroy.

Just as people once hated being told that Earth isn't the center of the universe, so goes the ego when it comes down to discovering the origin of our thoughts.

People still hate being told they're not actually the new Copernicus, no matter how much they think they are.

I got crazy obsessed with EvoLisa¹ back in the day and although there is nothing in common between that algorithm and those that make up training an LLM, I can't help but feel like they are similar.

¹ https://www.rogeralsing.com/2008/12/07/genetic-programming-e...