Caveman

“its matter-of-fact and short way of responding”

“When I'm using caveman (and especially cavekit), I don't have to spend quite so much energy on dealing with it building features I didn't ask for and don't want.”

“in the time I've actually come to like its matter-of-fact and short way of responding”

“anecdotally I do think it saves me quite a lot of time on reading LLM outputs”

“caveman is looking to be the only tool that actually doesn't regress on reasoning while taking costs down”

“it takes things too far in that direction, with "cave man" speech that sucks”

“I've found it effective so far. Chat output isn't nearly as flowery.”

“it has made my Claude experience vastly better”

“I want to spent less time reading.”

“In real sessions it doesn’t really save much longterm and made sessions more forgetful/take longer.”

“You should definitely explore caveman repo and other token-saving repositories.”

“Now I can’t stand caveman anymore. It is really frustrating working with it.”

“It also saves you tokens and it has been linked with more accuracy.”

“it cuts down on time spent digesting slop in general”

“answer like a cavemen, if llm talk like cavemen, the answers become shorter and more compressed”

“tools like RTK, Headroom, caveman mode and others do reduce input and output tokens that need to be processed”

“pointing to resource showing caveman, rtk saving just couple bucks on $926 bill”

“I want to see more operators try https://github.com/juliusbrussee/caveman”

“I tested both for weeks and they didn't really saved that much money for Opus model.”

“You can just add "be brief" to the prompt to replace the entire plugin. Same results.”

“Caveman only affects output tokens — thinking/reasoning tokens are untouched.”

“It really releases the stress slightly to call bugs, buggas and generally role play a humorous setting”

“It's a funny joke, but saving a couple hundred tokens in the final output is going to be negligible”

“the benchmark suggests it doesn't offer as much benefit as”

“turns out I never read the words that caveman omits, so to me it makes zero difference”

“What I appreciate is the terse answers it gives to me.”

“for THAT value of "better" it's not much different”

“Actually tried caveman mode yesterday and it made everything SO MUCH BETTER”

“If you're enjoying this thread, you have to make a stop over here”

“caveman sounds bad and is not as easy to understand compared to normal English”

“there are not many workarounds to minimize token usage unless you use caveman”

“changing something like this absolutely changes the behaviour of the models responses”

“extremely counter-productive if you care about the quality of its reasoning”

“I love this idea even if it's relatively insignificant in savings.”

“almost the entirety of the context spent is in file reads (for input) and reasoning (in output), you will barely save even 1%”

“I already enjoy reading its output more than vanilla so suits me well.”

“26.8 percent token reduction. zero observed degradation.”

“So my current position is: interesting idea, narrower claim than some people think, needs benchmarks”

“it does not reduce the token usage really”

“it will make my day not to have to read through entire essays about some trivial solution”