| ▲ | userbinator 5 hours ago |
| IMHO the overly-verbose default style of LLMs is the most annoying part of interacting with them, and I wish their masters would just tell them to be terse by default. Also, whatever happened to the word "its"? |
|
| ▲ | witx 5 hours ago | parent | next [-] |
| It's by default so you use all those tasty tokens. Kinda wish there was a deterministic, mostly terse, language to interact with computers |
| |
| ▲ | sodapopcan 4 hours ago | parent | next [-] | | > a deterministic, mostly terse, language Ah, like some sort of "programming language"? A weird idea, but it could work! | | | |
| ▲ | Etheryte 4 hours ago | parent | prev | next [-] | | It's called C. With all the undefined behavior it's mostly deterministic! | | |
| ▲ | anilakar 3 hours ago | parent | next [-] | | Look, we're always telling our bosses to stop micromanaging us. UB is just the compiler telling us to stop micromanaging it! | |
| ▲ | witx 4 hours ago | parent | prev | next [-] | | Right, because that's the only one. You're a bit rusty on your knowledge | | | |
| ▲ | well_ackshually 2 hours ago | parent | prev [-] | | Sorry, C isn't mostly terse, it's __builtin_mstly_trs() |
| |
| ▲ | Perz1val 2 hours ago | parent | prev | next [-] | | 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 | | |
| ▲ | dannyw an hour ago | parent [-] | | 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. |
| |
| ▲ | adrianN 4 hours ago | parent | prev | next [-] | | Terse and unambiguous seem to be at odds with each other. You might want to look into Lojban and similar constructions. | | | |
| ▲ | teaearlgraycold 4 hours ago | parent | prev | next [-] | | 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. | |
| ▲ | UqWBcuFx6NV4r 3 hours ago | parent | prev [-] | | It’s not. | | |
|
|
| ▲ | Terr_ 3 hours ago | parent | prev | next [-] |
| It's tied to the design. With humans, you have a train of thought which you can choose to represent in various ways--or not reveal them at all. In contrast, LLMs are make-document-longer machines being run over and over on alternating revisions of the document. Insofar as one might try arguing they have a "train of thought", it's made of the words/tokens. Everything they (don't-)emit is partly for the benefit of the next run, a clue or signpost (not-)present. Documents may be wordy as a form of concept-emphasis and consistent direction as opposed to a form of communication to the human. So a terse effect may require a layer of indirection and trickery: There's a verbose document (you'll still be charged for the tokens) with portions that are not "acted out" to the end-user. Imagine a film-noir movie script, where AI Detective's "I know Mickey couldn't have done it because" monologue is hidden, versus their terse dialogue "Too early to say." |
| |
| ▲ | Perz1val 2 hours ago | parent [-] | | > Imagine a film-noir movie script, where AI Detective's "I know Mickey couldn't have done it because" monologue is hidden, versus their terse dialogue "Too early to say." That's an idea. Bladerunner+noir like film, AIs hunt somebody on the run, an old human detective tries to catch them first (to save them or to kill them first, whatever's your propaganda). We're shown AIs constantly rambling scenarios and bruteforcing leads. Our old detective guy on the other hand barely says anything, spends most time drinking, smoking and talking to people, but somehow stays ahead. |
|
|
| ▲ | lelanthran 4 hours ago | parent | prev | next [-] |
| > IMHO the overly-verbose default style of LLMs is the most annoying part of interacting with them, and I wish their masters would just tell them to be terse by default. They don't know how to e terse. I've tried that a few months ago and gave up because the responses were almost incomprehensible! |
|
| ▲ | armchairhacker 4 hours ago | parent | prev | next [-] |
| I want to see more operators try https://github.com/juliusbrussee/caveman How does it affect agent accuracy? |
|
| ▲ | theshrike79 an hour ago | parent | prev | next [-] |
| Caveman mode legitimately works |
|
| ▲ | colechristensen 4 hours ago | parent | prev | next [-] |
| They ramble on because those words are for them, not for you. There is some amount of hiding this through "thinking" modes that are hidden by default, but still you have to remember that ALL THEY ARE are complex statistical machines for predicting the next symbol. |
| |
| ▲ | Frieren 4 hours ago | parent [-] | | > here is some amount of hiding this through "thinking" modes that are hidden by default, but still you have to remember that ALL THEY ARE are complex statistical machines for predicting the next symbol. 100% this. Too many people believes that chatbots "think". Text is all they do, it is impressive, but they need the text to generate more text. They being verbose is the point. |
|
|
| ▲ | 21asdffdsa12 5 hours ago | parent | prev | next [-] |
| Produce pre-compressed output in the harness? |
|
| ▲ | dyauspitr 3 hours ago | parent | prev | next [-] |
| No thank you. I want information when it’s working on things and what (atleast codex) does right now works for me. |
|
| ▲ | epolanski 3 hours ago | parent | prev [-] |
| [dead] |
