Technical Blog & Case Studies

Sol Ultra puts subagent orchestration inside the model. What cooperative subagents are, GPT-5.6 pricing and Codex availability, the METR cheating flag, and how it compares to Claude Code dynamic workflows.

GLM-5.2 is 2026's top open-weight coding model. Run it with llama.cpp and Unsloth quants - the hardware you need, the right quant for coding, and when a cloud API still makes more sense.

Claude Tag is Anthropic's persistent AI teammate in Slack. Wire it into engineering: connect MCP servers, scope channel access, use ambient mode safely, and control token costs.

Apple Core AI runs open-weight models like Qwen and Mistral on Apple Silicon with zero token cost. Convert PyTorch with coreai-torch, load via the Swift API, and quantize for mobile.

CVE-2026-42271 chains with the Starlette BadHost bypass (CVE-2026-48710) for unauthenticated RCE on the AI gateway. Detect exposure, upgrade to 1.83.7, rotate every key, and harden the MCP test endpoints.

Fable 5 launched at 2x Opus 4.8's price alongside the new fallbackModel setting. Chain configuration, the safety classifier that reroutes sessions to Opus 4.8, and a task routing table for all three models.

Dynamic workflows fan a task across up to 1,000 subagents. Which tasks justify the cost, how to bound the agent count, what ultracode costs, and when a single session still wins.

Three tiers of persistent memory in 2026: CLAUDE.md, MCP servers (agentmemory, claude-mem), and Anthropic's Memory tool plus Dreaming. Benchmarks and a decision matrix.

Install Qwen Code, fix the post-OAuth authentication mess, and see where Alibaba's open-source terminal agent actually beats Claude Code. CI/CD recipe + 1M-context reality check.

Gemini 3.5 Flash beats Gemini 3.1 Pro on agent benchmarks at $1.50/$9 per 1M tokens. When to route tasks from Claude Code, the thinking_level trap, and a 40-line MCP agent.

Gemini CLI stops on June 18, 2026. Step-by-step migration to the new agy binary, free-tier rate-limit math, and when to switch to Claude Code or Codex CLI instead.

Set up OpenAI Codex Security on GitHub end-to-end: connect a repo, edit the threat model, triage validated findings, ship patches as PRs. 74% TPR vs Semgrep 20% and Snyk 28% in independent testing.

Outcomes hands the agent a rubric, a separate grader checks every draft, and the loop iterates until the artifact passes. Rubric anti-patterns, the five result states, max_iterations tuning, and the cost math.

Claude Code 2.1.120 added claude ultrareview as a non-interactive CLI subcommand. The OAuth token gotcha, a copy-pasteable GitHub Actions workflow, --json parsing with jq, and a cost control playbook.

Three MCP servers can eat 72% of a 200K context window. The code execution pattern compares against dynamic toolsets and Tool Search, with a working Python build and Claude Code v2.1.121 alwaysLoad config.

After Anthropic's April 2026 postmortem revealed three Claude Code regressions, here is the practitioner playbook: pin the CLI, lock effort, allowlist models, add a regression-detecting stop hook, keep fixtures.

Defend Claude Code workflows against the April 2026 Comment and Control CVE. Tool allowlists, OIDC via Bedrock, script caps, egress blocks, and a before/after hardened workflow.

Workflow YAML, false positive tuning, token cost math, and a layered pipeline with Semgrep and Snyk for Anthropic's official security review action.

Install the ant CLI, create your first managed agent, and deploy it in under 10 minutes. YAML version control, scripting patterns, and CI/CD.

Track what you spend in Claude Code with built-in commands, hidden JSONL logs, and tools like ccusage. Plus 7 tips to cut token costs by 50%.

Practical decision framework for Claude Managed Agents vs the Agent SDK. Pricing breakdown with worked examples, MCP integration notes, and when to pick each option for your workload.

Anthropic locked Claude Mythos to 12 Project Glasswing partners. What the benchmarks, pricing, and restricted access mean for everyday developers, plus what to do while waiting for public release.

Tested all 4 Gemma 4 model sizes locally. Includes RAM requirements, Ollama setup, comparison with Llama 4 and Mistral, and a practical guide to picking the right variant.

Real production CLAUDE.md examples from my Next.js site. Learn the anatomy of an effective file, 7 common mistakes, and when to use hooks vs CLAUDE.md vs custom commands.

Set up your own personal AI assistant that works on WhatsApp, Telegram, Discord, and more. Self-hosted with persistent memory and proactive notifications.

Learn how to set up and use the Method CRM MCP Server to enable AI assistants like Claude to interact with your CRM data through natural language.