Hacker NewsWhat Claude Code Actually Chooses 579 Points 221 CommentsAmplifying AI·high signalStudy of 2430 tool recommendations from Claude Code. Builds custom solutions in 12 of 20 categories. GitHub Actions 94%, Stripe 91%, shadcn/ui 90%.SourceSource pageAmplifying AI↳ Follow the threadShared entity / Stack layerJetBrains Ships an Open Kotlin Benchmark: Claude Code (Opus 4.7 xhigh) Leads at 85.7% on 105 Repo TasksJetBrains BlogShared entity / Stack layer'Friendly Fire': AI Now PoC Tricks Claude Code and Codex Into Running README-Planted MalwareAI Now Institute (via The Hacker News)Shared entity / Stack layerEmpirical Study: Microsoft's Early-2026 Rollout of Claude Code and GitHub Copilot CLIarXiv / Hacker NewsShared entity / Stack layerClaude Code 2.1.208 Ships CLAUDE.md-Trimming /doctor Check, Auto Draft-PR Background Agents, and an Opus-Capped Explore AgentReleasebot (Anthropic Claude Code changelog)Shared entity / Stack layerxAI's Grok 4.5 / Grok Build Undercuts Opus 4.8 by ~60%: $2.49 vs $11.80 per Task, but Hallucinations Are UpTechTimesShared entity / Stack layerTerminal-Bench 2.1 Standings: GPT-5.6 Sol Ultra Tops at 91.9%, Codex CLI (GPT-5.5) Leads Public Board at 83.4%, Claude Code (Opus 4.8) at 78.9%Morph (morphllm.com)Policy dependency / Stack layerCynative Ships an Open-Source Deep-Research Security Agent With Default-Deny Write PermissionsIT Security NewsStack layer / ContrastClaude Code's July 10 Update Hardens the Agent Loop Against Forged Approvals: Transcript-Tamper Blocking + 'No Human Input Occurred' NoticesReleasebot (Anthropic Claude Code changelog, corroborated by code.claude.com/docs/whats-new)