Agentic AI: Good Upfront Design Pays You Back Later
Good upfront design pays you back later, not in theory, but in the ability to focus on small, high-value improvements instead of rebuilding the app.
Jul 7, 20267 min read35
Command Palette
Search for a command to run...
Latest articles
Can Fable 5 Finish Off the Other Frontiers?
Can Anthropic's Fable 5 justify its staggering cost and live up to the massive hype to unseat the top specialized models? I ran Ship-Bench against the model to find out, stacking it up directly agains
Jun 15, 202612 min read16
Can the Mid-Tier Models Stack Up Against the Bigger Siblings?
Can you really justify paying flagship prices when the mid-tier models may already be good enough? The original comparison started with Gemini 3 Flash vs. Claude Sonnet 4.6, then Gemini 3.5 Flash arri
Jun 1, 202613 min read19
Antigravity CLI First Impressions: Fast, Rough, and Not Ready
Google has officially replaced Gemini CLI with the new Antigravity CLI and launched it alongside Gemini 3.5 Flash, which became the default model for the new CLI experience. That made the launch more
May 21, 20265 min read
Do Open Frontier Models Have A Chance Against Closed Models ?
Which of the new open-ish frontier models has the best chance to stand up against closed-source models on both cost and quality? I ran Ship-Bench against Kimi K2.6, Qwen 3.6 Plus, and DeepSeek v4 Pro
May 13, 202612 min read33
Can Gemma 4 Beat Gemini 3.1 Pro at Coding?
Is a $20/month Google AI Pro account worth it versus running Gemma 4 31B on OpenRouter pay-as-you-go? This Ship-Bench run was designed to answer that question across a realistic coding workflow rather
Apr 27, 202611 min read41
An AI Benchmark That Tests Real Coding Workflows
Developers face a real choice: pick a coding model or agent based on synthetic benchmarks that look great but do not predict actual project work. The problem is no longer whether models can score well
Apr 19, 20268 min read41
Vector Similarity, Zero Client JS: Decoupled Analytics on a Side Project Budget
A leaderboard for DumbQuestion.ai sounds simple. Track the most asked questions, display them. Done. Except people never ask the same question the same way twice. I was curious about how creative user
Mar 31, 20266 min read24Self-Awareness, Prompt Injection, Search Intent... and darkness
Building DumbQuestion.ai wasn't just about choosing the right LLM and calibrating personas. Once those were working, I hit a series of fun technical problems that reminded me why I actually enjoy soft
Mar 31, 20265 min read3