AI Briefing#token-budget
The latest AI and developer news about #token-budget, with the original source and a short summary.
The latest AI and developer news about #token-budget, with the original source and a short summary.
The Claude Code system prompt grew by 166 tokens in 2.1.124 and shrank by 87 tokens in 2.1.126.
Evidence has emerged that Anthropic lowered Claude Code's default prompt cache TTL from 1 hour to 5 minutes.
Even when shown their budget, coding agents couldn't cut their own spending.