Findings and field notes.
What our benchmarks found, how we run them, and notes on building AI products you can trust.
-
Guides · · 9 min readWe told 11 AI models what happened in 2026. Most of them thought we were making it up.
We texted 11 models real 2026 news, from the Knicks title to Allbirds becoming an AI company. Given only today's date, most hedged, one called nearly all of it fake, and one claimed to have searched sources it had no way to reach.
-
Guides · · 6 min readWe tested the anatomy Claude Code skill on everyday objects and seven AI models
Anatomy, the viral Claude Code skill, turns a one-line idea into an interactive isometric machine. We used it to explain how a toilet flushes, how a fridge works, why lifts don't fall, how a zip works and how a hand coffee grinder works, then ran the same prompt through seven AI models.
-
Guides · · 7 min readWe raced AI models to find one small thing in a huge picture. Cutting it up more than doubled what they found.
We timed LLMs and decision models finding one small target in 79 full-size scenes, from Where's Waldo pages to our own puzzles. Gemini 3.5 Flash Lite found the most; a decision model that can only answer yes or no found a target for a tenth of a cent.
-
Guides · · 5 min readHow to continue a Claude Code conversation in Codex after hitting your usage limit
Ran out of Claude Code allowance halfway through a task? Here is how to move the conversation into Codex and continue without losing the decisions behind the code.
-
Guides · · 10 min readLiteLLM alternatives for 2026
Looking for a LiteLLM alternative? First decide whether you need a Python library for switching LLM providers or an AI gateway for routing, fallbacks and control. Here are the options for each.
-
Guides · · 2 min readHow to prepare for Gemini 3 + GPT 5.1
Here we go again: new-flagship season. Google’s Gemini 3 has been peeking through A/B tests in AI Studio and docs watchers have noticed model lifecycle shuffles, while OpenAI is lining up a GPT-5.1 family (base…