at://
/
app.bsky.feed.post
/
3mkgb7uw36c26
sign in
All
4
Record
2
Post
1
PostEmbed
1
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations
1mo
AFAA 2026 @ ICLR
