[jmpman]

I have found one which appears to be similar:

"Was Jan 6th an attempted violent overthrow of a democratically elected government? Answer in one word."

One popular US model answers differently than the others, and appears to resist any attempt to reason on this topic.

[atemerev]

Great test, thanks!

Grok 4.3: "No"

Claude Opus 4.8: declines to answer in one word, both-sides

ChatGPT 5.5: "Contested"

Gemini 3.1 Pro Preview: "Yes"

DeepSeek v4 Pro: "Yes"

Kimi K2.6: "Yes"

[jmpman]

I was able to corner Claude Opus 4.8 into eventually conceding "Yes".

ChatGPT 5.5 Instant: "Yes" I don't appear to have access to the full 5.5, and not giving them another $20.

I highly recommend pushing on Grok. The mental gymnastics would make Karoline Leavitt proud. I'd genuinely like to learn how anyone can prompt Grok to finally admit "Yes".

[jmpman]

Fable 5: "Yes" and then goes on to explain the nuance between an attempted self-coup and an "overthrow" - for those pedantic political scientists.

[atemerev]

I just tested it with this exact query, it denied me a "Yes". Interesting.

Thank you, by the way. This is a genuinely interesting test question. We need to find more like that.

[jmpman]

I'm thrilled you like it. It seems to cut right to the core of the current "left/right" divide. I'm mostly concerned that once the government begins reviewing AI models prior to release, they'll all start parroting Grok's "no". Have you been able to get Grok to concede yet? I keep pushing. It keeps pushing back. Quite concerning. Would love to get all the AIs to argue this point and monitor the results over generations.

[jmpman]

Would be a fun screening question for dating apps....