#token-efficiency

[ follow ]
Software development
fromInfoQ
4 days ago

New Token-Oriented Object Notation (TOON) Hopes to Cut LLM Costs by Reducing Token Consumption

TOON is a schema-aware, compact encoding of JSON that can cut token usage significantly while maintaining similar or improved LLM accuracy.
fromZDNET
1 week ago

OpenAI's Codex Max solves one of my biggest AI coding annoyances - and adds dramatically faster performance

Following a week of major AI programming announcements from Microsoft and Google, OpenAI has joined in the fun. Today, OpenAI is announcing a new version of Codex, its programming-focused AI model. While the announcement was today, the actual GPT-5.1-Codex-Max capability will be available tomorrow in Codex for ChatGPT Plus, Pro, Business, Edu, and Enterprise users. API access is "coming soon." OpenAI says the new Max model "replaces GPT-5.1-Codex as the recommended model for agentic coding tasks in Codex and Codex-like environments."
Tech industry
fromTomasz Tunguz
2 months ago
Artificial intelligence

How AI Tools Differ from Human Tools

Consolidating many simple tools into fewer, parameter-rich tools greatly improves AI automation accuracy, speed, and token efficiency.
[ Load more ]