I discovered yesterday that the “amazing thing that comes out of OpenAI” is Sol, due to its token efficiency.

Dollar for tokens, Sol and Fable are the same price.

However, Sol uses (literally: in testing) around 10-100x less output tokens compared to Fable for the same task.

We run our frontier models nearly 24/7, so switching to Sol will save us around $500 per day.

And, due to less guardrails, Sol also performed better, and we lost less tokens due to guardrails shutting down sessions (I feel like it’s illegal to take $50 of someone’s token money and then shut down a session with guardrails before they get an answer, and yet Anthropic do it to us constantly… either take our money and commit, or trigger the guardrails immediately)

▲

resonious 2 hours ago | parent | next [-]

Sol is way cheaper than Fable by the token.

▲

dannyw an hour ago | parent | prev | next [-]

We’ve literally saved tens of millions of dollars already (no exaggeration! already 8 digits) by switching to Luna for many workloads at my company.

The amount of workloads we can shift with an advisor model pattern continues to grow.

It’s seriously amazing.

▲

minraws 3 hours ago | parent | prev | next [-]

Wait isn't Fable like 2x more expensive if we compare under 272k tokens

▲

ChadMoran 3 hours ago | parent [-]

The comment you're replying to almost feels like it was written by a bot or am I crazy?

▲

theplumber an hour ago | parent | next [-]

Peak under your skin a bit. Something weird is going on. I think we are bots/robots(sic)

▲

w4yai 3 hours ago | parent | prev | next [-]

I agree. Weird to use <“> and <”> characters. Maybe written on phone, but certainly not on keyboard.

	▲	jrflo 2 hours ago \| parent \| next [-]
		Other languages use different characters for quotes, if anything that's an indication that's not written by a LLM because it's not favoring the standard English character. https://en.wikipedia.org/wiki/Quotation_mark#Specific_langua...
	▲	gunalx 2 hours ago \| parent \| prev [-]
		Common on non us keebs though.

▲

jlund-molfese 3 hours ago | parent | prev [-]

What kind of bot would say `less guardrails` instead of `fewer guardrails`? I guess someone could instruct an LLM to deliberately make mistakes, but isn't that too paranoid?

	▲	qgin 34 minutes ago \| parent \| next [-]
		We’re reaching transvestigation levels of people trying to spot AI text everywhere they look
	▲	DrewADesign 2 hours ago \| parent \| prev [-]
		“include common grammatical imperfections and awkwardness common in casual message board interactions.” I’m not saying that’s what’s happening here, but a high school student told me that’s basically what they do to make papers not sound like AI.

▲

gtree 2 hours ago | parent | prev [-]

You could say the token usage is "load-bearing".