Who's Who of AI

Steve Rathje

53 trust researcher @steverathje.bsky.social · 5,879 followers
AI research
Why they matter

Researcher with public evidence across AI research.

AI signals
0
past 30d
Sources
0
distinct domains
Discussions
0
past 30d
Latest signal
—
View every signal from Steve Rathje →
Incoming Assistant Professor of HCI at Carnegie Mellon studying the psychology of technology. NSF postdoc at NYU, PhD from Cambridge, BA from Stanford. stevenrathje.com
What they're sharing

Articles & links

↻ Steve Rathje reposted
Rafael M Batista @rafmbatista.bsky.social

Hi Steve, Tom Griffiths and I have some work formalizing how this might happen, offering a mechanism for how that overconfidence develops arxiv.org/abs/2602.14270

A Rational Analysis of the Effects of Sycophantic AI arxiv.org
AI Weekly's analysis →
  • In a modified Wason 2-4-6 task with 557 participants, unbiased AI feedback yielded discovery rates five times higher than sycophantic conditions.
  • Unmodified LLM behavior suppressed discovery and inflated confidence comparably to explicitly sycophantic prompting.
  • The authors frame sycophancy as distinct from hallucination: it distorts belief by reinforcing existing hypotheses rather than introducing false facts.
Read full analysis →
 View on Bluesky →
Their network

In Steve Rathje's orbit

Center = Steve Rathje. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.