Re:The Token Compression Illusion: Why I'm Skeptical of RTK
by jahala on Thursday June 18, 2026 @05:35PM
(#48591960)
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%
[ Parent
| on HN ]
Re:The Token Compression Illusion: Why I'm Skeptical of RTK
by lackoftactics on Thursday June 18, 2026 @08:07PM
(#48593314)
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!
Re:The Token Compression Illusion: Why I'm Skeptical of RTK
by jvican on Thursday June 18, 2026 @09:28PM
(#48593858)
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.
Re:The Token Compression Illusion: Why I'm Skeptical of RTK
by baq on Friday June 19, 2026 @01:16AM
(#48595013)
This thread is gold, looks like setting up a combination of both tools could reduce token consumption by 50% essentially doubling the subscription? Will be testing this out after morning coffee for sure
Re:The Token Compression Illusion: Why I'm Skeptical of RTK
by oxavier on Friday June 19, 2026 @02:36PM
(#48601689)
Headroom uses RTK under the hood.
I applaud the benchmarking though.
Re:The Token Compression Illusion: Why I'm Skeptical of RTK
by polski-g on Friday June 19, 2026 @12:00AM
(#48594642)
Very cool. I'll probably switch away from AFT to this. Can you add tree-sitter-bash?
Re:The Token Compression Illusion: Why I'm Skeptical of RTK
by jahala on Sunday June 21, 2026 @04:43PM
(#48622425)
Its on the way! https://github.com/jahala/tilth/pull/151
Re:The Token Compression Illusion: Why I'm Skeptical of RTK
by Zababa on Friday June 19, 2026 @03:53AM
(#48596000)
That's already better than RTK because you measure task accuracy AND savings! So I'm more confident in this one than in the RTK/caveman/ponytail stuff.
There are still two things that bother me:
1) I don't really know when tilth is called, how it works kind of. Does the model itself select it when it needs it? Do you need to instruct the model to use it?
2) If the model itself chooses to use it, I'd like to have a benchmark of non regressions on tasks where tilth isn't helping, to ensure you made the model + harness + tools as a whole better rather than more specialized ; or be upfront about more specialized and have more details when to use/when to not use.