$ cat /var/log/thoughts

AI Coding + Performance

Posts matching all selected tags.

Claude Code vs Codex Limits, Measured in the Same Unit

Claude Code vs Codex limits, measured across 28 days and 56.8 billion tokens. Why token counts cannot predict quota burn, and what to read on each side instead.

Meta AnalysisAI CodingClaude CodeDeveloper ToolsComparisonMonitoringPerformance1 min read · Jul 28, 2026

Why expensive models make terrible execution subagents

Subagent model selection has one costly default. Reasoning models obey their own traces 15.6% of the time, so here is where to pin model and effort.

OpinionAI CodingClaude CodeDeveloper ToolsArchitecturePerformance1 min read · Jul 28, 2026

Token-Compression Skills Do Not Survive Measurement

Token compression skills report savings the invoice never shows. Cache reads carry 87 percent of an agent bill, and cutting tokens can push the cost up.

Meta AnalysisAI CodingClaude CodePerformanceDeveloper ToolsCaching1 min read · Jul 28, 2026

7 Free Ways to Stop ChatGPT From Eating Your CPU, RAM, and Disk

Fix ChatGPT performance without spending a cent: diagnose high CPU, reduce RAM-heavy threads, stop disk churn, trim Git load, and disable unused MCP servers.

GuidesAI CodingPerformanceProductivityDeveloper Tools1 min read · Jul 24, 2026

Cut MCP Round-Trip Overhead by Looping Inside the Tool

MCP round-trip overhead can balloon a task from 2,000 to 150,000 tokens. Move the loop inside one MCP tool to collapse N calls into a single round-trip.

GuidesClaude CodeAI CodingMCPTypeScriptPerformanceAutomation1 min read · May 30, 2026