Author of the text here. I will be honest with why I wrote it, the rtk ai looks very odd to me as software engineer, the number of stars, no mention of accuracy and how management is pushing that stuff to optimize costs. Now people are wrapping every possible command in rtk and trying to handle all major possible commands and decide which output you should get.

▲

jahala 4 hours ago | parent | next [-]

Would sincerely love to hear your thoughts on https://www.github.com/jahala/tilth - it’s a different approach than RTK, benchmarked to reduce cost per correct answer by ~40%

▲

lackoftactics an hour ago | parent [-]

Looked at your repo, even starred. On the surface, I like your approach a bit better. It looks like your idea sits at the space between semantic search and compressing tokens. I was into semantic search before, but mostly trying to vectorize codebase instead of tree sitter and couldn’t make the semantic search work for me. Thanks for sharing!

	▲	jvican 3 minutes ago \| parent [-]
		An ex colleague is working on Headroom, a much more legit alternative to RTK. They provide accuracy benchmarks in the repo and are transparent about the compression algorithms used for the different output types. I liked their approach a lot better than RTK and thought it might be relevant for you. https://github.com/chopratejas/headroom

▲

ianwalter 6 hours ago | parent | prev [-]

Why didn’t you offer any real world usage numbers to illustrate your point? I found this unhelpful.

▲

fumeux_fume 2 hours ago | parent | next [-]

https://en.wikipedia.org/wiki/Brandolini%27s_law

	▲	lackoftactics an hour ago \| parent [-]
		Thanks for the link! I thought I know every obscure law and I was so wrong.

▲

lloyd-christmas 5 hours ago | parent | prev | next [-]

I read another post oddly similar earlier today that has more explicit data on that authors codebase: https://codepointer.substack.com/p/cutting-llm-token-costs-w...

TLDR; ~3-4% savings to actual API costs with rtk, caveman, and headroom combined, but nothing tangible on if those cost reductions came at a cost of quality. By their calculations, rtk saved them $4.96 on a $926 bill.

	▲	bcollins34 2 hours ago \| parent [-]
		^recommend reading this one

▲

lackoftactics 5 hours ago | parent | prev [-]

That’s the fair point. The rtk promotional posts point to 60-90% tokens savings and there is no mention how they perform accuracy wise. The commenter below did great job pointing to resource showing caveman, rtk saving just couple bucks on $926 bill. Thanks, Llyoyd Christmas for linking to useful substack