CCTest · Blog
Daedalus-150M Reverses the Usual Recipe for CPU-Friendly Inference
Inference & Serving
cctest.ai

Daedalus-150M Reverses the Usual Recipe for CPU-Friendly Inference

Daedalus-150M was designed from its deployment target backward: single-user, one-token-at-a-time decoding with 4-bit weights on a conventional CPU. By replacing two-thirds of its attention blocks with cache-bounded short convolutions, the model targets the memory costs that become dominant at longer contexts.

Read more
CCTest · Blog
AgentMercury Turns Business Scenarios into Verifiable Worlds for Agents
AI Agents
cctest.ai
AI Agents

AgentMercury Turns Business Scenarios into Verifiable Worlds for Agents

AgentMercury proposes a framework that synthesizes persistent, executable business environments instead of generating isolated tasks for specific benchmarks. Its authors report 4,783 environments across 14 industries and 50 countries, with gains on enterprise workflows and selected out-of-domain evaluations.

Read more
CCTest · Blog
Uncle Bob’s AI Coding Experiment: Less Line-by-Line Review, but Architecture Still Needs Humans
Coding AI
cctest.ai
Coding AI

Uncle Bob’s AI Coding Experiment: Less Line-by-Line Review, but Architecture Still Needs Humans

Uncle Bob is experimenting with handing implementation to AI agents and moving human effort toward automated quality controls and architectural review. The approach reduces routine inspection, but it does not replace judgment about system structure, security, or business context.

Read more