The Token Compression Illusion: Why I'm Skeptical of RTK

Post by mumin00 » Fri, Jun 19, 2026, 3:26 AM UTC

Post by polski-g » Fri, Jun 19, 2026, 4:00 AM UTC

jahala wrote: post #60

lackoftactics wrote: post #30

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.

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%

Post by saaspirant » Fri, Jun 19, 2026, 4:43 AM UTC

tontinton wrote: post #54

cityofdelusion wrote: post #22

I am glad articles like this are finally starting to get some momentum around what I call the LLM magic box industry. From caveman mode to RTK to semantic search and everything in between. Developers have become magicians that cast spells instead of engineers. It sucks at work especially with everyone so sure that their magic spell is the one for ultimate token savings. My criteria are: if it’s not in a harness it’s…

Totally wrong, you underestimate the frontier's incompetence in anything other than building LLM models (ehm ehm flickering TUI for a year "written like a game engine"). I ran a bunch of benchmarks and there are proven ways to reduce tokens while achieving the same results (finding the same CVEs / finding the same bugs in CRs, etc...). See https://maki.sh , it's my own little proof.

Post by baq » Fri, Jun 19, 2026, 4:53 AM UTC

blubber wrote: post #24

cityofdelusion wrote: post #22

I am glad articles like this are finally starting to get some momentum around what I call the LLM magic box industry. From caveman mode to RTK to semantic search and everything in between. Developers have become magicians that cast spells instead of engineers. It sucks at work especially with everyone so sure that their magic spell is the one for ultimate token savings. My criteria are: if it’s not in a harness it’s…

There is a conflict of interest, though.

Post by baq » Fri, Jun 19, 2026, 5:16 AM UTC

jvican wrote: post #88

lackoftactics wrote: post #83

Earlier quoted context omitted.

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!

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