The idea itself is sound: If you can reduce the signal-to-noise ratio in the con... | Hacker News

Hacker Timesnew | past | comments | ask | show | jobs | submit

arcanemachiner 33 days ago | parent | context | favorite | on: The Token Compression Illusion: Why I'm Skeptical ...

The idea itself is sound: If you can reduce the signal-to-noise ratio in the context window, then that's a good thing.

Whether or not RTK actually does this has not been established. I would be glad to see some proper benchmarks done on the actual difference this tool makes (not some meaningless "up to 90%" type of language).

celrod 33 days ago | [–]

I found this, which has some: https://arxiv.org/pdf/2605.28876 TLDR: RTK does not look good according to the author's benchmark.

lackoftactics 33 days ago | [–]

I was wondering if that impacts the accuracy, obviously the rtk output wasn't in the training dataset, but maybe it doesn't matter at the end

Consider applying for YC's Fall 2026 batch! Applications are open till July 27.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact