How to Evaluate a New Model From Evidence Instead of Hype: A Walk Through 60 Claude Fable 5 Cases
EvoLink
Command Palette
Search for a command to run...
Archive
39 posts published so far
How I Configured Claude Code as an Architect: 10 Settings, Grouped by What They Fix
EvoLink
A Practical Seedance 2.0 Prompt Structure for More Controllable AI Video
EvoLink
Testing Claude Code Dynamic Workflows With a 111-Agent Research Run
EvoLink
Gemini 3.5 Flash vs Claude Opus 4.7 vs GPT-5.5: Which Model for Which Agent Task (May 2026)
EvoLink
Claude Code HTML Artifacts: When Markdown Is the Wrong Output
EvoLink
Building with OpenAI's New Realtime Voice Stack: Architecture Decisions and Trade-offs
EvoLink
Managed Agents Dreaming, Outcomes, and Orchestration: Architecture and Tradeoffs
EvoLink
Managed Agents Dreaming, Outcomes, and Orchestration: Architecture and Tradeoffs
EvoLink
Claude Code Prompt Caching: Architecture, Pitfalls, and Cost Optimization
EvoLink
Codex v0.128.0 Architecture: From Stateless Sessions to Goal-Driven Agents
EvoLink
Claude Opus 4.7: Migration Guide for Production Teams
EvoLink
Karpathy's 4 LLM Coding Rules, Packaged as a CLAUDE.md: Architecture Decision and Tradeoffs
EvoLink
DeepSeek V4 API: Flash vs Pro Decision Guide for Engineering Teams
EvoLink
DeepSeek-V4 Deep Dive: Huawei Ascend Optimization, Sub-$0.30 Pricing, and the Architecture That Makes It Work
EvoLink
GPT Image 2 + Seedance 2.0: The Two-Stage AI Video Production Workflow
EvoLink
Google Deep Research: Agentic Research Platform, Not Just a Better Summarizer
EvoLink
Claude Design: LUI Over GUI — What Anthropic's Design Tool Actually Changes
EvoLink
GPT Image 2: Why Text Rendering in AI Images Is the Real Breakthrough
EvoLink
Migrating from Claude Opus 4.6 to 4.7: Breaking Changes, Token Cost Reality, and Rollout Strategy
EvoLink
How Hermes Agent Is Rethinking the Agent Memory Problem: Architecture and Design Tradeoffs
EvoLink
Happy Horse 1.0: Benchmark Results, Seedance 2.0 Comparison, and What Developers Should Know
EvoLink
Claude Mythos Preview: Benchmark Data, Exploit Chains, and What Changes for Security Engineering
EvoLink
I Evaluated 3 AI Video APIs for a Production Project. Here's How They Compare.
EvoLink
Seedance 2.0 vs Sora 2: I Tested Both with Identical Prompts — Here's the Full Breakdown
EvoLink