Skip to main content

Turning AIs Into Cavemen Is Actually A Good Idea

 

 

Token limits have been the number 1 problem of vibecoding. Aside from high usage, vague prompting and inefficient context management are two key causes that contribute to this problem. Tokens are counted from two things, the user’s input and agent’s output. You can have the best prompt in the world, but if your AI puke a Shakespearean essay for each response, your token will reach its limit faster. Similarly, if your prompt is too long, your token usage will also skyrocket.


Prompting

Prompting seems easy enough, but the reality is, if you want quality output, the input must be of similar quality. Here are some tips you can try to achieve a better, token-efficient prompt.

Stick to English language only

Certain languages may use higher tokens. Switching between languages might not be a good idea. Sure you can control your input prompt, but the output may use more tokens.

Extremely short input

Do not use ‘please’ or ‘thank you’. Get rid of filler words. Straight to the point. Talk like a caveman. ‘I want to make a fire by heating up wood, thanks.’ is bad, ‘Make fire with wood’ is good. 

Extremely short output

You caveman. Is agent caveman too? Install the caveman extension to make sure the output is always just as short as the input. Installing the extension is easy, and it's properly documented there, so go check it out.

Do not refactor outputs

Why ask your agent to refactor a code they just gave you? Instead, make sure your prompt is clear enough so the output code doesn’t need to be refactored afterwards.


If you want to check how many tokens your prompts are using, verify it on this tokenizer website 


Context Management

Set reference points

Mention files to refer (eg: @file_path/file) and mention functions to refer. Do not directly paste code into the prompt input, mentioning is better. Code outputs that are based on existing code always use less token than a completely new code output. 

Long context is expensive

Start a new session for a new task. Clear conversation once you’re done. Regularly review context usage with /context command. 

Use context management engines

This one is a bit ‘open’. There is no one-solution-fix-all here. Some use a custom made skill, some use extensions, some use softwares. It’s completely up to you. The key is to make sure your agent has just enough context to ensure good token efficiency while still having a good response. One tool that I use is Vexp.


TLDR

Why use many words when few do tricks? Embrace caveman conversation to use fewer tokens. Hope this post helps your vibecoding sessions.

Location: 43800 Dengkil, Selangor, Malaysia

Comments

Post a Comment

Popular posts from this blog

🗑️ Clear storage Mac OS

  🗑️ Clear storage Mac OS 1: Clear system cache: Go to Finder > Go > Go to Folder, then type in "~/Library/Caches" and hit enter. Select all the folders inside the Caches folder and delete them. 2: Clear system logs: Go to Finder > Go > Go to Folder, then type in "/var/log" and hit enter. Select all the files inside the Log folder and delete them. 3: Remove unused language files: Go to Finder > Go > Go to Folder, then type in "/Library/Languages" and hit enter. Delete all the language folders you don't need. 4: Uninstall unused apps: Go to the Applications folder and delete the apps you don't use. 5: Clean up system files: Use a system cleaning tool like CleanMyMac X to scan and remove unnecessary system files. 6: If you have npm installed, clear the caches once in a while with ‘sudo npm cache clean --force’ 7: If you have ionic projects, open the ‘.angular’ folder and delete the ‘cache’ folder inside it.
Post a Comment
Read more

Setup existing IONIC project in local

Setup existing IONIC project in local  Steps: clone git repo install ionic -  npm install -g @ionic/cli masuk folder repo project install npm dependencies -  npm install run ionic project -  ionic serve buka android studio / xcode -  ionic cap open $var  - $var = ‘android’ atau ‘ios’. ada dua je option, replace $var dgn dua option tu sync changes vscode & dkt android studio / xcode -  ionic cap sync good luck Common issues: dependency conflict check https://www.npmpeer.dev/ utk tengok version yg compatible try naikkan/turunkan version dependency yg keluar dkt error. tembak je sampai hilang error g radle issue try upgrade gradle. kalau tak boleh, try remove folder android & build semula e rror cocoapod make sure install xcode make sure install cocoapod error java  home not found utk mac, buka ~/.zshrc & masukkan chang es dkt VSC tak masuk android studio / xcode try ionic cap sync try quit & buka semula cordo va.variables.gradle no...
Post a Comment
Read more

Vulnerabilities in Dependencies

Vulnerabilities in Dependencies - A Lesson from 4Chan Case Study: The 4Chan Security Breach The Neglect 4Chan had not updated its project dependencies since 2009. The Vulnerability One specific dependency was publicly known to have multiple critical vulnerabilities: Ghostscript.  Ghostscript Vulnerability Reports (Snyk) Attack Vectors: Local File Inclusion (LFI): The system processed PDF files without verifying if the uploaded file was actually a PDF. Remote Code Execution (RCE): After a successful injection, attackers could run malicious scripts directly on the server. The Wake-Up Call This event serves as a modern reminder of the critical importance of keeping dependencies up to date. Dependencies Audit & Status These are some of the dependencies commonly used. mPDF (Fixed) Vulnerability: Deserialization of untrusted data (similar to the 4Chan/Ghostscript exploit). Risk: Affects all versions lower than 7.1.8. aws/aws-sdk-php (Fixed) Path Traversal Affects versions lower t...
Post a Comment
Read more