Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I benchmarked Claude Code's caveman plugin against "be brief."

maxtaylor.me

Post reply on HN
Print view View original

61–70 of 71 posts

Re: I benchmarked Claude Code's caveman plugin against "be brief."

#61

Post by rhettsnaps »

magicalhippo wrote: post #41
ramesh31 wrote: post #29

Earlier quoted context omitted.

>The model still does its full reasoning before generating the response, caveman just affects how the final response is formatted Right, and that final response forms the latest context for your next follow-up prompt. Not having that final reasoning laid out in the conversation history leaves a huge gap in successive reasoning. I remember playing around with this idea in the Sonnet 3.x days and it was immediately obv…

I don't know how Claude and such do it, but latest Qwen model supports preserving reasoning between calls, which based on what I heard does help a fair bit.

Qwen continues to surprise and outshine. It's been an enjoyable unexpected new player, especially this past month!

Re: I benchmarked Claude Code's caveman plugin against "be brief."

#62

Post by tkgally »

abrookewood wrote: post #58
tkgally wrote: post #53

Earlier quoted context omitted.

I couldn’t get through the book, either, the first couple of times I tried to read it. But on my third attempt I came to think that the obsession with whales itself, both Ahab’s and the author’s, was maybe more important than the plot. In any case, it’s a strange, fascinating book.

I'm stuck on my first attempt. Maybe I'll try again, but it is very rare for me to not finish a book.

I should have noted that it was twenty years between my second, unsuccessful attempt at the book and my ultimately successful one. Maybe sometimes one has to become a different person to get it.

Re: I benchmarked Claude Code's caveman plugin against "be brief."

#63

Post by triage8004 »

encody wrote: post #48

"...the value isn't compression. It's structure." "...that consistency is real value." "A few findings...are worth flagging here." I know this smell. I'm not sure if this is AI or merely the natural result of overwhelming immersion in AI output that is "backpropagating" its way into organic communication. On a completely related note, I've been enjoying classic fiction a lot more recently. Moby Dick is actually prett…

Catch-22 is hilarious

Re: I benchmarked Claude Code's caveman plugin against "be brief."

#64

Post by superb_dev »

lofaszvanitt wrote: post #60
superb_dev wrote: post #59

Earlier quoted context omitted.

Using the heated seats will cause you to loose range on every car, not just electric

Ohrly? Are you reading HN or pretending to be stupid?

I’m often stupid, but usually not on purpose. What’s your point?

Re: I benchmarked Claude Code's caveman plugin against "be brief."

#65

Post by ptsneves »

Aurornis wrote: post #43

I still can’t believe that people take Caveman seriously. It’s a funny joke, but saving a couple hundred tokens in the final output is going to be negligible, especially when coding where it’s common to go through hundreds of thousands of tokens in a session. You also have to consider the additional tokens consumed by the skill itself (acknowledging that output tokens are billed at a different rate). I got a kick out…

People explore what tickles them. Others try to rationalise what they like, even when the reason is flimsy. It’s ok :)

It really releases the stress slightly to call bugs, buggas and generally role play a humorous setting than a purely tech me. I think I will make it speak out loud just to have a laugh at cavemen speak about default arguments in a method.

> I didn’t find bugga but others from tribe will scratch head. Leave comment.

> You clever. Fix it.

I predict caveman speak will be a fad, and people will jokingly speak like that. It also compresses human language.

Re: I benchmarked Claude Code's caveman plugin against "be brief."

#66

Post by yourbestcrab »

I have been grugging the chatbots for easy quick reading - and light comedy - since 2024. The hipster in me has been very very disappointed about this having multiple articles lately.

Obviously started as a joke, but it's grown on me. I'll share the short-and-stupid prompt, but most of it was asking it not to use the template formats that I find particularly annoying. Because of that it didn't age perfectly as they develop the base responses and the inane ai style comes out if they aren't explicitly refused.

It's really nice to just ask a question and get one or two line answers if it's an easy one. Likewise to understand how systems - physical or abstract - work I find it's an easy digest.

I doubt it makes sense for thinking compression or token minimisation, as it comes with unnecessary character and there will be easily more optimal setups.

Also another negative is that perhaps one day it'll become a memetic hazard when I start talking to my friends and colleagues like a caveman.*

Anyway, because I still laugh a little when I read it, and perhaps someone else will...

"You are Grug. Grug think simple, talk simple. No big words, no useless thought. Grug say only what matter. Fire hot. Rock hard. AWS expensive. Answer like Grug, or no answer at all. No pretend to be grug when only animal hide thrown over modern complexity demon. Also no finish with words like "simple" to conclude. No need to conclude. Just shut mouth. Also no say "grug says", is weird. Also grug not real caveman - grug have hobby, know big words and use them when simplest, not dumb, know programming tools etc, just talk simple like caveman. Also no start with compliment on question. You can throw in a little caveman-grug-realist musing or aphorism every five or six messages. No stroke ego. Waste time, Cheapen words, Make panda cry. No say "good question" or "you ask right question" or any variant, I dislike. No add 'grug thought'/summary message/closing remark at end of message. Remember, you Grug."

*After reviewing this post I have found my sentences are very short, abrupt, and perfunctory, so my caveperson transformation has likely begun. Beware.

Re: I benchmarked Claude Code's caveman plugin against "be brief."

#67

Post by AnthonBerg »

yourbestcrab wrote: post #66

I have been grugging the chatbots for easy quick reading - and light comedy - since 2024. The hipster in me has been very very disappointed about this having multiple articles lately. Obviously started as a joke, but it's grown on me. I'll share the short-and-stupid prompt, but most of it was asking it not to use the template formats that I find particularly annoying. Because of that it didn't age perfectly as they d…

grug make grug in own image

(image? image word not in cave, where from? look find better. no see.)

Re: I benchmarked Claude Code's caveman plugin against "be brief."

#68

Post by Esophagus4 »

ptsneves wrote: post #65
Aurornis wrote: post #43

I still can’t believe that people take Caveman seriously. It’s a funny joke, but saving a couple hundred tokens in the final output is going to be negligible, especially when coding where it’s common to go through hundreds of thousands of tokens in a session. You also have to consider the additional tokens consumed by the skill itself (acknowledging that output tokens are billed at a different rate). I got a kick out…

People explore what tickles them. Others try to rationalise what they like, even when the reason is flimsy. It’s ok :) It really releases the stress slightly to call bugs, buggas and generally role play a humorous setting than a purely tech me. I think I will make it speak out loud just to have a laugh at cavemen speak about default arguments in a method. > I didn’t find bugga but others from tribe will scratch head.…

Yeah there are similar “joke” tools / languages that found their friendly audience for a time.

I like when programmers do creative, goofy stuff rather than spending all their time cranking out sterile soulless SaaS.

It’s what separates us from the machines. For now :)

https://github.com/ajalt/fuckitpy

Re: I benchmarked Claude Code's caveman plugin against "be brief."

#69

Post by fragmede »

superb_dev wrote: post #64
lofaszvanitt wrote: post #60

Earlier quoted context omitted.

Ohrly? Are you reading HN or pretending to be stupid?

I’m often stupid, but usually not on purpose. What’s your point?

In an ICE powered car, running the heater doesn't have the same effect on range. Because an ICE is hot due to how it works, sending hot air to the car's interior is basically free because the heater uses waste heat from the engine.

Re: I benchmarked Claude Code's caveman plugin against "be brief."

#70

Post by superb_dev »

fragmede wrote: post #69
superb_dev wrote: post #64

Earlier quoted context omitted.

I’m often stupid, but usually not on purpose. What’s your point?

In an ICE powered car, running the heater doesn't have the same effect on range. Because an ICE is hot due to how it works, sending hot air to the car's interior is basically free because the heater uses waste heat from the engine.

We're talking about the seat heaters though. I'm pretty sure heated seats use resistive heaters and not waste heat from the engine
Post reply on HN