@cHHillee: I've realized when people are talking about how many tokens they use, they're usually including cached input tokens... …
Summary
The author criticizes the common practice of including cached input tokens in discussions about token usage in AI models.
Similar Articles
Everyone in AI wants to reduce token use. What if one of the biggest sources of wasted tokens is relational buffering?
The article explores how relational buffering—extra tokens from misaligned intentions—might be a significant source of waste in AI interactions, proposing 'tokens per resolved intention' as a metric to reduce computational cost while preserving fidelity.
@jxnlco: Big token wants you to spend 40% tokens in <div> tags
A tweet criticizes how AI models waste tokens on HTML <div> tags, suggesting that tokenizers inefficiently allocate 40% of tokens to structural elements.
Human typing habits and token counts
A blog post exploring how human typing habits like typos, shorthand, filler words, and whitespace affect token counts in OpenAI and Claude tokenizers, noting that common misspellings can inflate token usage and costs without changing meaning.
@pallavishekhar_: How to reduce token usage in AI Agents? Let's understand. AI Agents use LLMs to think, plan, and recommend tools. Every…
This thread shares strategies to reduce token usage in AI agents, including prompt caching, context summarization, using smaller models, trimming tool outputs, subagents, RAG, and tight system prompts.
@_avichawla: A smarter Claude model burns more tokens, not fewer! And it's not a minor 3-5% difference. But 54% higher token usage. …
The article analyzes why smarter AI agents like Claude consume more tokens when interacting with human-centric backends like Supabase due to inefficient context discovery. It introduces InsForge, an open-source backend tool designed for agents that provides structured context to significantly reduce token usage and manual interventions.