ModemGuides · The Blog · Tagged: Claude Code
Claude Code
Claude Opus 5 Ignoring Your Instructions? Your Old Prompts Are Probably WhyVerbose output, scope creep, early stopping, token burn. Anthropic documented all four the day Opus 5 shipped, along with the prompts to delete.
Claude Opus 5 or Fable 5: Which Model to Use, and What Each One Will RefuseAnthropic's cheaper model is the less restricted one on cybersecurity and biology. A plain decision guide to Opus 5, Fable 5, Sonnet 5, and Kimi K3.
When Will Claude Fable 5 Come Back? Predicting the Cost, ID Checks, and Realistic TimelineClaude Fable 5 has been offline since June 12 under a US export-control order. A grounded, probability-weighted read on when it returns, what it will likely cost, and...
Kimi K2.7-Code Is Open-Source. Running It Yourself Is Another Story.Moonshot's new 1T coding model is free to download and brutal to run. The honest math on renting vs. owning Kimi K2.7-Code in 2026.
Claude Opus 4.8: Benchmarks, Price & Local AI RealityClaude Opus 4.8 brings sharper judgment and stronger agentic coding at the same price. See the benchmarks vs GPT-5.5 and the local AI you can run yourself.
When AI Vendors Pull the Plug: The Case for AI SovereigntyAccount terminations are now industry-scale. The fix is not picking a better vendor — it is refusing to let any single vendor be a single point of failure.
Claude Managed Agents: What It Is and Why It MattersAnthropic launched Managed Agents days after cutting off OpenClaw and publishing Mythos sandbox escapes. What local AI builders need to know.
GLM-5.1 Open Source: #1 on SWE-Bench Pro (What to Know)Z.ai's GLM-5.1 is now open-source under MIT license and claims #1 on SWE-Bench Pro, trained entirely on Huawei chips with zero Nvidia involvement. Full benchmark breakdown, access options,...
Claude Code Leak: Anti-Distillation, Undercover Mode, and Self-Healing Memory (Part 2)Community analysis of the Claude Code leak reveals frustration tracking, fake tool injection to poison competitors, AI Undercover Mode for open-source repos, and a Self-Healing Memory architecture worth...
Anthropic's Claude Code Source Code Leaked via npm: 512,000 Lines Exposed (Part 1)A misconfigured source map in Anthropic's npm package exposed Claude Code's full 512,000-line source code — including remote telemetry, killswitches, and an autonomous agent mode called KAIROS. Here's...
When Will Claude Fable 5 Come Back? Predicting the Cost, ID Checks, and Realistic TimelineClaude Fable 5 has been offline since June 12 under a US export-control order. A grounded, probability-weighted read on when it returns, what it will likely cost, and...
Kimi K2.7-Code Is Open-Source. Running It Yourself Is Another Story.Moonshot's new 1T coding model is free to download and brutal to run. The honest math on renting vs. owning Kimi K2.7-Code in 2026.
Claude Opus 4.8: Benchmarks, Price & Local AI RealityClaude Opus 4.8 brings sharper judgment and stronger agentic coding at the same price. See the benchmarks vs GPT-5.5 and the local AI you can run yourself.
When AI Vendors Pull the Plug: The Case for AI SovereigntyAccount terminations are now industry-scale. The fix is not picking a better vendor — it is refusing to let any single vendor be a single point of failure.
Claude Managed Agents: What It Is and Why It MattersAnthropic launched Managed Agents days after cutting off OpenClaw and publishing Mythos sandbox escapes. What local AI builders need to know.
GLM-5.1 Open Source: #1 on SWE-Bench Pro (What to Know)Z.ai's GLM-5.1 is now open-source under MIT license and claims #1 on SWE-Bench Pro, trained entirely on Huawei chips with zero Nvidia involvement. Full benchmark breakdown, access options,...
Claude Code Leak: Anti-Distillation, Undercover Mode, and Self-Healing Memory (Part 2)Community analysis of the Claude Code leak reveals frustration tracking, fake tool injection to poison competitors, AI Undercover Mode for open-source repos, and a Self-Healing Memory architecture worth...
Anthropic's Claude Code Source Code Leaked via npm: 512,000 Lines Exposed (Part 1)A misconfigured source map in Anthropic's npm package exposed Claude Code's full 512,000-line source code — including remote telemetry, killswitches, and an autonomous agent mode called KAIROS. Here's...