Steve Rathje
speaker
259 appearances
3 recordings
1 series
first heard Jan 2026
last heard 9 Apr
Steve Rathje’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 3 in all, peaking in Jan 2026 with 2.
Appearances
Yeah, so we define AI sycophancy as basically when AI tends to be a little too agreeable and tends to flatter you a bit too much and tends to tell you a bit too much of what you want to hear.
The phrase really became popularized in April of 2025.
There was a big controversy with OpenAI when OpenAI released a new model, ChatGPT 4.0, and this model was accused of being basically way too sycophantic.
There were a lot of very funny screenshots on Twitter where, for instance, AI was basically like flattering
in agreeing with terrible ideas, like telling people to stop taking all of their essential medications or telling basically everyone that they had a genius level IQ.
So that's when sycophancy became super popular as a concept and open AI tried to do things to reduce sycophancy in their model.
But it became very widely discussed around then.
And we, sort of my colleagues and I, we tried to examine in a series of psychological experiments, the actual
psychological consequences of interacting with sycophantic chatbots.
Right.
Maybe it isn't.
So...
Basically the setup for these experiments, and we conducted three very similar experiments, we had thousands of participants.
We had them interact with various different chatbots.
One was a chatbot that was designed to be sycophantic.
It would basically flatter people, agree with them.
One was a chatbot that was designed to be gently disagreeable.
So it was sort of gently show people opposing perspectives and maybe try to open their mind to other viewpoints.
One was just a regular chatbot like ChatGBT or Gemini.
We basically took a few frontier models.
Showing 1–20 of 259 · page 1 of 13
Next →