ByManish Shahi·Software Engineer • AI Developer
I runmanish.sh. I write aboutAItools and howLLMsbehave when you push them.
This is part of theInside LLMsseries — interview a chat model about how it thinks, then check the careful bits against published research. TheKimi K2.6 entrycame first; this is the DeepSeek follow-up.
My first question sounded simple:What do you actually know about yourself?
I expected marketing. Instead, DeepSeek sorted its answer into observation,inference, and guess. That was the moment I realized this interview might actually be interesting.
It drew pipelines like an engineer at a whiteboard. Then it called itself an unreliable witness. Sounded honest. After the chat, I opened the public papers anyway — and that is where the story splits.
Noweightdumps. No prompt leaks. One long interview, checked against arXiv. Where DeepSeek said “I am guessing,” I keep that label. Scroll tointeractive labsat the end.
Quick note:One chat, exported 21 July 2026. DeepSeek said latest version,knowledge cutoffMay 2025, not labelled asDeepSeek-R1. Self-report, not a whitepaper.
Treat it like a documentary. Question → short reply → my reaction → diagram or short list → takeaway → hook. Interview notes are not proofs. For architecture numbers, skip ahead to the paper check. Each chapter opens with a one-line gloss of its main terms.
Most “how does this model work” posts start from papers. I started from a chat.
Me:“Which model are you? What do you actually know about your own architecture — and what are you only guessing?”
DeepSeek:It answered in three buckets — observation, inference, guess — before I even asked for that framing.