I don’t know about the rest of you, but the bulk of my token usage is not what I type in - it’s that data the AI is processing for me. I’m shocked they even got an 8% reduction.
Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test
11–20 of 44 posts
Re: Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test
#12Yes all the caveman spoke English like its freaking Flinstone. Like wtf is the caveman dilect, just english words with some randomly skipped? Why not try with actual other human languages and see if there is a token benefit in savings
Sounds like some good research. You should pursue it.
lol - so easy a caveman can do it.
Re: Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test
#13If you just want a smaller vocabulary, use French? If your goal is to communicate to an LLM, maybe saving tokens isn't the all in win, unless you like reading assert gronkHitThing(true)
French text is somewhere around 10-30% longer than the corresponding English text. I would guess much of what you save on smaller vocabulary is lost on the lengthened text.
Re: Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test
#14If you just want a smaller vocabulary, use French? If your goal is to communicate to an LLM, maybe saving tokens isn't the all in win, unless you like reading assert gronkHitThing(true)
French text is somewhere around 10-30% longer than the corresponding English text. I would guess much of what you save on smaller vocabulary is lost on the lengthened text.
What would matter more is the token length, depends how well your tokenizer was trained on french I guess.
Re: Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test
#15https://groups.google.com/g/alt.nerd.obsessive/c/EGuKIN_4dME...
alt.nerd.obsessive FAQ v1.4
In the episode where they were filming the Radioactive Man movie [1995], the comic book store guy tells Bart that he can find out the star of the RM movie. He promptly posts a message to alt.nerd.obsessive which states "Need know star RM pic". This information is relayed through the nerd world until it reaches a nerd hiding under the table at a meeting of movie moguls casting the film. He relays back the answer immediately (Rainier Wolfcastle).
Re: Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test
#16Yes all the caveman spoke English like its freaking Flinstone. Like wtf is the caveman dilect, just english words with some randomly skipped? Why not try with actual other human languages and see if there is a token benefit in savings
Me mechanic not speak English. But he know what me mean when me say "car no go", and we best friends. So me think: why waste time, say lot word when few word do trick?
Re: Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test
#17Yes all the caveman spoke English like its freaking Flinstone. Like wtf is the caveman dilect, just english words with some randomly skipped? Why not try with actual other human languages and see if there is a token benefit in savings
Me mechanic not speak English. But he know what me mean when me say "car no go", and we best friends. So me think: why waste time, say lot word when few word do trick?
To see world
Re: Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test
#18Why not Mandarin Chinese? Logographic is pretty compact.
Also, this really should be more precise that it’s talking about neo-caveman. Legit caveman no speak English.
Re: Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test
#19Yes all the caveman spoke English like its freaking Flinstone. Like wtf is the caveman dilect, just english words with some randomly skipped? Why not try with actual other human languages and see if there is a token benefit in savings
Sounds like some good research. You should pursue it.
Someone definitely should
Re: Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test
#20I think it's funny this works somewhat, but that's not what the goal is, IMO. The goal is to have the model do this internally in its "thinking" stage. On the very rare occasions in the past where gpt5 leaked its true internal thinking, the "CoT" was itself kinda similar. Instead of the open source "so the user wants me to... but wait... maybe I should... blahblah...", GPT5 was using internal traces like "try x.. no.. try y... no.. from x yes then z yes...". That's probably more token saving, or faster responses, if you can get the model to remain accurate.