A lot of those things you mentioned have sticking power because they’re familiar to folks and migrating to something else is a big deal.

I can’t imagine most people would be able to tell the difference between Sonnet and GLM 5.2. If the infrastructure around the model you’re using doesn’t change, then swapping models is extremely easy.

▲

arikrahman a day ago | parent | next [-]

I agree with swapping models making it easy. With openrouter, I just change the provider. With reasonix harness, cache hits are basically free. And that's with unsubsidized American providers like Digital Ocean or cloudflare.

▲

argee a day ago | parent | prev | next [-]

Indeed, as it gets more commoditized it feels more like swapping electricity providers. Who cares whether you get your electricity from IBM or the state of Texas? An amp is an amp.

▲

fragmede a day ago | parent [-]

That's an interesting question. What if we did care? Is this amp from burning dinosaurs or from the sun or from fission? What if we could tag power as coming from oil vs renewables? how would that affect our habits?

	▲	argee a day ago \| parent [-]
		We care indirectly through cost. Hydroelectric, solar, or wind power are often among the cheapest electricity sources, for example. Beyond that, no we don't care. That's why if people want change we leverage policy on cost, via subsidies, surcharges, taxes, tariffs, what have you. To a consumer, an amp remains an amp — so they get the cheap one.

▲

QuercusMax a day ago | parent | prev [-]

I'm using pi-coder with just the free-tier models I can get on openrouter / opencode / kilocode. When I run out of quota on one model I often switch to another model in the same session, and it generally works just fine.

	▲	Bolwin a day ago \| parent [-]
		When I use it for fiction, I generally switch models 2-3 times per response. It's basically normal