🖼️0036 Days of Claude Code Logs: Silent Model Switching, 11.5x Efficiency GapDEV Community·Recca Tsai·24 days ago#137fVqnT#subagent#how#most#model#agent#output+3 more🧰Tag tools✨Add tagContinuing the cache TTL audit series, this time breaking down by model. The server silently switched main agent models three times (Opus 4.6 → Sonnet 4.6 → Opus 4.7 → Sonnet 4.6), and Claude Code autonomously assigns sub-agent models.… Read more15s0Read later0Read More
🖼️00My Subagents Kept Lying to Me — So I Wired Ed25519 Verification Into Our Own Protocol StackDEV Community·Vilius·26 days ago#VZq5hVZ9#layer#ai#python#subagent#verification#verify+4 more🧰Tag tools✨Add tagFrom Dev.to - opensource: My Subagents Kept Lying to Me — So I Wired Ed25519 Verification Into Our Own Protocol Stack15s0Read later0Read More
🖼️00I ignored Claude Code's subagents until I realized what I was missingXDA·Mahnoor Faisal·28 days ago#9NKo1Afi#sensa#community#claude#code#tools#agent+4 more🧰Tag tools✨Add tagFrom XDA Developers: I ignored Claude Code's subagents until I realized what I was missing15s0Read later0Read More
📰00The #2 cause of runaway Claude API costs (it's not infinite loops)DEV Community·Atlas Whoff·about 1 month ago#bSrq0mF0#webdev#javascript#typescript#programming#prompt#subagent+5 more🧰Tag tools✨Add tagWhen developers worry about runaway AI API costs, they think about infinite loops. An agent that...15s0Read later0Read More
