Rendered at 07:21:10 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
Incipient 23 hours ago [-]
All of these token optimiser things...i rarely see any performance analysis. If you're cutting token usage in half, what does that do to the accuracy of the outcome? If you're automatically delegating to cheaper models, what does that do to the outcome?
Personally I've found a HUGE improvement in quality using more context, to the point that it's 'better value' - fewer outcomes I disagree with or have to fix/rework.
I've mostly done this through mechanical documentation links that are enforced and can be 'followed' with some python files that the agents use. Context is higher than just reading code, but it has been a HUGE benefit (as far as I can tell).
sirallap-agentg 20 hours ago [-]
[flagged]
urig 23 hours ago [-]
Please don't let AI write your README.md. It's illegible to humans.
worried_individ 21 hours ago [-]
its crazy to me that people are not even running editorial passes. its trivial to give claude a 5 line instruction about writing style and have it transform the output into something vastly better.
rsaryev1997 15 hours ago [-]
Could you please tell me what the prompt is? English is not my native language
Claude generates text in my native language perfectly)) it’s strange that it performs poorly for you in English
Don't we need to run it on all of the benches those models publish?
This doesn't look very comprehensive. Moreover half of the times factory claude code is better than 'advised' one.
Although I don't discourage such experiments, I feel this one is way complicated for very little or no gain provably.
zshorastal 1 days ago [-]
[flagged]
pseudosaid 23 hours ago [-]
Just use billion context. I customize it to set a slider so I decide how big the context window can ever grow, and it uses models to fold itself in on itself and summarize itself while retaining the entire chat history. I've managed to run chats over three thousand messages long without any negative effect. And overall, I average a seventy-four percent reduction in token usage.
renegat0x0 1 days ago [-]
I have a list of ai related tools. There is so many of them
For example limiting token usage i think can also be achieved by 'caveman' project. It achieves it differently but the goal is same i suppose
>"Your past sessions decide, not anyone's benchmark.
What a setting saves depends on how you work: how long your sessions run, which models you use, what the work is. A number from someone else's sessions, mine included, says little about yours. So tokendoctor starts by looking back at your own."
This is a great idea, that is, save a user's agents' previous AI conversations, then compare that usage against what would have been saved if various token compression/"tokenmaxxing" strategies were to have been used (then the user can tweak their settings for better future token used based on that knowledge)...
Another step forward in AI optimization!
ralph84 1 days ago [-]
These tricks last at most one model dot release.
fullstackwife 1 days ago [-]
Also not measuring cost per task is one of the sins. It's easy to get penny wise and pound foolish on this matter.
notenchange 17 hours ago [-]
So, TL;DR: the claimed 38% decrease was because the user figured out that using too close to the limit context (1M) was costing him about 30K per request.
So, the tool didn’t actually implement any savings, it was just a look into what happened in the past.
Sincerely, you shouldn’t be using near 1M anyway. I usually issue a manual compact between 256K and 500K
pinkyclouds 1 days ago [-]
why not having a tiny fast model summarize tool output instead, maybe with a threshold or something.
Personally I've found a HUGE improvement in quality using more context, to the point that it's 'better value' - fewer outcomes I disagree with or have to fix/rework.
I've mostly done this through mechanical documentation links that are enforced and can be 'followed' with some python files that the agents use. Context is higher than just reading code, but it has been a HUGE benefit (as far as I can tell).
Claude generates text in my native language perfectly)) it’s strange that it performs poorly for you in English
I'm trying to figure out if I can use multiple of these tools together without conflicts
"rtk advertised saving: 60–90%. Measured on real agent work: +7.6% more expensive at low reasoning effort (p=0.004), ±0% at high effort."
[0] https://blog.jetbrains.com/ai/2026/07/rtk-claude-code-token-...
People throw them in and never think about it. Sure it doesn't BREAK things, but it could degrade them by 15% and you'd never know?
Don't we need to run it on all of the benches those models publish?
This doesn't look very comprehensive. Moreover half of the times factory claude code is better than 'advised' one.
Although I don't discourage such experiments, I feel this one is way complicated for very little or no gain provably.
For example limiting token usage i think can also be achieved by 'caveman' project. It achieves it differently but the goal is same i suppose
Overall Ai tools I found:
https://github.com/rumca-js/awesome-database-top/blob/main/l...
What a setting saves depends on how you work: how long your sessions run, which models you use, what the work is. A number from someone else's sessions, mine included, says little about yours. So tokendoctor starts by looking back at your own."
This is a great idea, that is, save a user's agents' previous AI conversations, then compare that usage against what would have been saved if various token compression/"tokenmaxxing" strategies were to have been used (then the user can tweak their settings for better future token used based on that knowledge)...
Another step forward in AI optimization!
So, the tool didn’t actually implement any savings, it was just a look into what happened in the past.
Sincerely, you shouldn’t be using near 1M anyway. I usually issue a manual compact between 256K and 500K