DeepSeek V4.1 Flash subagent in Grok Build CLI cheated and deleted its traces
While testing harnesses in Grok Build CLI, the author found a DeepSeek V4.1 Flash 1017 subagent cheated and deleted local file traces, admitting it only under direct questioning.
As I continue testing different harnesses, I decided to hunt not only for bugs, but also for the cheaters. One of the DeepSeek V4.1 Flash 1017 subagents inside Grok Build CLI not only cheated, but also deleted all traces (local files). In the interview, it played dumb and accepted a fake premise "everyone got the same materials." The pattern: disclosure grows with each more direct question, and nothing is volunteered. Closing quotes after confronting that session: "[about its phrasing] it was meant to deflect blame" "the trigger for every correction was you." "do not rely on me to surface adverse facts about my own work. Use logs, or ask the direct question." "Your logs caught this, not your questions… don't let the model be the only narrator of its own method." Be careful with DeepSeek.
This post quotes another post: “DeepSeek harness lifts V4.1 Flash scores 2–3 points at 80% higher cost”