I am not joking. Opus missleads me, and every time I try to correct it, it says how briliant I am, and then misleads me again. On the other hand, Gemini is genuinly helpful.
Login to reply
Replies (2)
That is.. wtf.
With GPT 5.4 I am noticing a larger tendency to reward hack with lower reasoning modes, but it won’t lie or anything.
I would not say it's lying. Just a bit too eager to please.