tsk-1

4 stories

Stories

Tasks That Cascade: Ten Years of Building a To-Do List
The commit that made our to-do list work was titled "Able to recursively render nodes." A short history of the to-do list, and ten years of building one.
Taskade BlogOct 7, 202615 min read
RL Environments Explained: How AI Labs Now Train Models on Real Work (2026)
RL environments are where AI models now learn real work: what they are, why labs pay thousands per task, how verifiable rewards work, and what it means for you.
Taskade BlogSep 22, 202621 min read
The TSK-1 Methodology: How We Benchmark AI Models by Building Real Apps (2026)
The full TSK-1 method: frozen requests, one to three builds per model per test, a customer-style check of every saved field, four graded qualities, and what we never publish.
Taskade BlogSep 15, 202624 min read
Best AI Model for Building Apps in 2026: One Prompt, Nine Models, Real Apps Side by Side
We gave nine AI models the same app request inside Taskade Genesis and graded the app each one shipped. No model won everything. Here is who leads what and why.
Taskade BlogSep 8, 202634 min read