It's by default so you use all those tasty tokens.
Kinda wish there was a deterministic, mostly terse, language to interact with computers
It's by default so you use all those tasty tokens.
Kinda wish there was a deterministic, mostly terse, language to interact with computers
> a deterministic, mostly terse, language
Ah, like some sort of "programming language"? A weird idea, but it could work!
Nah, it'll never catch on. We don't have the technology.
Obviously I meant within the next 6 to 18 months!
It's called C. With all the undefined behavior it's mostly deterministic!
Look, we're always telling our bosses to stop micromanaging us. UB is just the compiler telling us to stop micromanaging it!
Right, because that's the only one. You're a bit rusty on your knowledge
I see what you did there.
Sorry, C isn't mostly terse, it's __builtin_mstly_trs()
Kinda, more output tokens usually correlates with better benchmark scores. Ideally LLMs would keep that in their thinking section, then draft a response (what they write currently), then output something short. It'd consume even more tokens, but we wouldn't see that text
Most modern LLMs (especially frontier ones) are large token hogs because they draft, check, re-draft, the content (whether an output message; or a code diff) sometimes multiple times in the thinking block.
When you see a thinking summary like "Now writing the function..."; the raw thinking is actually writing the function in its internal thinking. Occasionally, the summariser misses and you get to see the raw text from models like Opus.
You can also try an open weight LLM like Qwen3.6 and see something that probably resembles the shape of frontier model thinking in some loose way.
Terse and unambiguous seem to be at odds with each other. You might want to look into Lojban and similar constructions.
Ithkuil's mad morphology allows it to pack a lot of fine detail into very short sentences.
https://ithkuil.net/03_morphology.html
If such a language existed, it would surely take a human years of study to become proficient at it.
Loglan?
A lot of users are subsidized (if you're in doubt, consider the wealth of free users).
It's a shotgun approach to answering questions. If it's terse it might only mention 1 of 10 facts it could provide, and that might not be the one you're looking for. So they just say a fuck ton of words and are more likely to meet the needs of everyone asking your question. If they miss it you'll prompt it again and they have to perform a second pass of inference, which costs them more money.
Lisp
It’s not.
It's settled then.