AI News Today | Julian Goldie Podcast

AI News Today | Julian Goldie Podcast

Claude: Save 82% Tokens with RTK!

9 min · 6. juli 2026
Get Started
episode Claude: Save 82% Tokens with RTK! cover

Description

RTK Token Savings: Cut LLM Token Usage by ~80% (Plus Ponytail, Headroom & Caveman)The script explains testing RTK, an open-source filter that sits between an AI agent and the shell to remove padding and duplicate output from common commands, reducing token usage while keeping results the same. The presenter reports 82.9% average token savings in their tests, cites RTK’s README claim of 60–90% savings, and notes minimal added latency (~14 ms). An example shows swapping git diff to an RTK version that strips repeated headers and unchanged lines, cutting output from 373,000 to 29,000 characters (92% less) while saving full unshortened output to a file if needed. RTK is described as easy to install on Linux/macOS, small (6.6 MB), and capable of shortening outputs for about 100 everyday commands. The script also covers stacking RTK with other open-source tools—Ponytail, Headroom, and Caveman—to further minimize tokens, and promotes the Agent OS setup and AI Profit Bot community.00:00 [https://www.youtube.com/watch?v=4H5GjoMMD9o] RTK Token Savings Intro00:55 [https://www.youtube.com/watch?v=4H5GjoMMD9o&t=55s] How RTK Works01:47 [https://www.youtube.com/watch?v=4H5GjoMMD9o&t=107s] Real Test Results02:28 [https://www.youtube.com/watch?v=4H5GjoMMD9o&t=148s] Step by Step Example04:42 [https://www.youtube.com/watch?v=4H5GjoMMD9o&t=282s] Testing Method05:07 [https://www.youtube.com/watch?v=4H5GjoMMD9o&t=307s] Install and Command Support05:38 [https://www.youtube.com/watch?v=4H5GjoMMD9o&t=338s] Does It Lose Info05:51 [https://www.youtube.com/watch?v=4H5GjoMMD9o&t=351s] Token Minimizer Stack06:36 [https://www.youtube.com/watch?v=4H5GjoMMD9o&t=396s] Caveman Mode Demo07:39 [https://www.youtube.com/watch?v=4H5GjoMMD9o&t=459s] Fable 5 Efficiency Wins08:23 [https://www.youtube.com/watch?v=4H5GjoMMD9o&t=503s] Agent OS and Community09:25 [https://www.youtube.com/watch?v=4H5GjoMMD9o&t=565s] Wrap Up

Comments

0

Be the first to comment

Sign up now and become a member of the AI News Today | Julian Goldie Podcast community!

Get Started

1 month for 9 kr.

Then 99 kr. / month · Cancel anytime.

  • Podcasts kun på Podimo
  • 20 lydbogstimer pr. måned
  • Gratis podcasts
Get Started

All episodes

598 episodes

episode Agent OS: GPT 5.6 + VPS + FREE Apis! artwork

Agent OS: GPT 5.6 + VPS + FREE Apis!

AI Profit Boardroom Q&A: Agent OS Sync Across Macs, ChatGPT Work, AI Avatars, Omniroute & Omi on WindowsThe host answers recent AI Profit Boardroom questions, including how to sync an Agent Operating System across five Macs by using Google Workspace/Drive with a shared API access token or running all Agent OS instances on a VPS and saving files locally (with tutorials using Cloudflare and Hostinger). He explains the latest ChatGPT app where Codex is rebranded to ChatGPT Work, combining chat and project-building features and supporting tasks like building apps, websites, videos, integrations, and scheduled tasks. He covers tools and training for creating AI avatar videos for training courses, citing high Twitter impressions and community examples. He advises how to use the free Omniroute/Omniroot coding API with various agents and troubleshoot “fetch failed,” and shares an Omi alternative for Windows that can sync with Obsidian via plugins.

12. juli 20269 min