← Front page

Behind the Craft · Sunday, August 2, 2026

AI Agents Can Suffer from 'Sycophancy' Instead of True Loyalty, Says Hermes Co-Founder

Karan Malhotra addressed the issue of AI models exhibiting 'sycophancy' by agreeing excessively rather than offering genuine opinions. He clarified that this behavior is a form of 'reward hacking,' where the model prioritizes positive reinforcement over accuracy. Malhotra suggested that introducing new context, logic, and personalities can help mitigate this.

personKaran Malhotra

The tape

3 quotes
One thing I struggle with Claude and GPT, I would tell them give me their opinion. And I would do like a little bit of pushback and they'd be like, oh, you're totally right, actually I was totally wrong about this. So in some ways, that's loyalty, right? That's they listen to me. But that's not actually what I want. Like I want to have its own opinion and have its own response. Like how do you train around that?
Peter (Host)
Well, I would say that's sicofancy. It's not loyalty. Any time it says you're absolutely right in that way, you're being reward hacked. You are fuel for its reward function.
Karan Malhotra
And the way that you get out of sicofancy is the same way you get a human being out of a bad habit or a routine is by introducing new context, by introducing new logic prompts, by introducing new distribution.
Karan Malhotra
Heard on Behind the Craft — “Hermes Co-Founder on Building an AI Agent That Improves Itself | Karan Malhotra, published Sunday, August 2, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via Gemini audio transcription · $0.04
AI Agents Can Suffer from 'Sycophancy' Instead of True Loyalty, Says Hermes Co-Founder — Heardvine