Caveman: Why use many token when few token do trick

Though I do use Claude Code, is it possible to get this for Github Copilot too?

I mean, I assume you run into the same problem as Kevin in the office; that sort of faux-simple speech is actually very ambiguous.

(Though, I wonder has anyone tried Newspeak.)

I tried this with early ChatGPT. Asked it to answer telegram style with as few tokens as possible. It is also interesting to ask it for jokes in this mode.

Are there any good studies or benchmarks about compressed output and performance? I see a lot of arguing in the comments but little evidence.

> If caveman save you mass token, mass money — leave mass star.

Mass fun. Starred.

Why use lot word when few word do fine.

Better: use classical Chinese.

What is that binary file caveman.skill that I cannot read easily, and is it going to hack my computer.

Or you could use a local model where you’re not constrained by tokens. Like rig.ai

Ok but when the model is responding to you isn’t the text it’s generating also part of the context it’s using to generate the next token as it goes? Wouldn’t this just make the answers…dumb?

me like that

Caveman need invent chalk and chart make argument backed by more than good feel.

grug have to use big brains' thinking machine these days, or no shiny rock. complexity demon love thinking machine. grug appreciate attempt to make thinking machine talk on grug level, maybe it help keep complexity demon away.

I like

This is exactly what annoys me most. English is not suitable for computer-human interaction. We should create new programming and query languages for that. We are again in cobol mindset. LLM are not humans and we should stop talking to them as if they are.

LOL it actually reads how humans reply the name is too clever :').

Not sure how effective it will be to dirve down costs, but honestly it will make my day not to have to read through entire essays about some trivial solution.

tldr; Claude skill, short output, ++good.

Funny how people are so critical of this and yet fawn over TOON

Unfrozen caveman lawyer here. Did "talk like caveman" make code more bad? Make unsubst... (AARG) FAKE claims? You deserve compen... AAARG ... money. AMA.

I'd be curious if there were some measurements of the final effects, since presumably models wont <think> in caveman speak nor code like that

Oh come on now one referenced this scene from the office??

https://youtu.be/_K-L9uhsBLM?si=ePiGrFd546jFYZd8

Oh, another new trend! I love these home-brewed LLM optimizers. They start with XML, then JSON, then something totally different. The author conveniently ignores the system prompt that works for everything, and the extra inference work. So, it's only worth using if you just like this response style, just my two cents. All the real optimizations happen during model training and in the infrastructure itself.

I didn’t comment on this when I saw it on threads/twitter. But it made it to HN, surprisingly.

I have a feeling these same people will complain “my model is so dumb!”. There’s a reason why Claude had that “you’re absolutely right!” for a while. Or codex’s “you’re right to push on this”.

We’re basically just gaslighting GPUs. That wall of text is kinda needed right now.

kevin would be proud

I don't know about token savings, but I find the "caveman style" much easier to read and understand than typical LLM-slop.

Mongo! No caveman

I was actually worried about high token costs while building my own project (infra bundle generator), and this gave me a good laugh + some solid ideas. 75% reduction is insane. Starred

Deep digging cave man code reviews are Tha Shiznit:

https://www.youtube.com/watch?v=KYqovHffGE8

caveman multilingo? how sound?

[dead]

[dead]

[dead]

[dead]