Menu

1 / 7

Inside DeepSeek: Reverse Engineering an AI Assistant by Interviewing Itself · manish.sh

Hacker News·3 months ago
#uA95kx3V
#manish#deepseek#chat#model#token
Reading 0:00
15s threshold

I run manish.sh . I write about AI tools and how LLMs behave when you push them.

This is part of the Inside LLMs series — interview a chat model about how it thinks, then check the careful bits against published research. The Kimi K2.6 entry came 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.

Screenshot from the DeepSeek interview chat used in this post.

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.

No weight dumps. No prompt leaks. One long interview, checked against arXiv. Where DeepSeek said “I am guessing,” I keep that label.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.