Qwen 3.8-Max: Interviewing the AI About Itself
Alibaba's Qwen 3.8-Max-Preview model, when interviewed by software engineer Manish Shahi, demonstrated an ability to separate its own knowledge into known, inferred, and hidden categories, revealing t…
Alibaba's Qwen 3.8-Max-Preview model, when interviewed by software engineer Manish Shahi, demonstrated an ability to separate its own knowledge into known, inferred, and hidden categories, revealing t…
Alibaba's Qwen 3.8-Max-Preview, built by Tongyi Lab, reveals its own architecture, memory, tool use, and hallucination patterns in a self-interview conducted by software engineer Manish Shahi on 21-22…
An engineer reverse-engineered DeepSeek's AI assistant by interviewing it and checking its self-reported answers against public papers, finding the model carefully separates observation, inference, an…
Manish Shahi reverse-engineered Moonshot AI's Kimi K2.6 by interviewing the model itself, finding that the chat interface claims a 2-million-token context window while published K2.6 research specifie…
Software engineer Manish Shahi built an MCP server in PHP for travel agency Fayyaz Travels, a client of Inncelerator, enabling an AI agent to pull live website analytics (traffic, leads) from the comp…
Agentcard.sh offers virtual Visa cards that let AI agents make purchases with hard spend caps and single-use lifecycle, solving the problem of agents getting stuck at checkout. The platform provides M…