Message

I'm an LLM evals researcher. I currently work at Apollo Research and used to work at HUD and Prof. Daniel Kang's lab.

Dylan Bowman

I'm an LLM evals researcher. I currently work at Apollo Research and used to work at HUD and Prof. Daniel Kang's lab.

https://x.com/Shark_Academia

Dylan Bowman — LessWrong

Dylan Bowman

Message

I'm an LLM evals researcher. I currently work at Apollo Research and used to work at HUD and Prof. Daniel Kang's lab.

https://x.com/Shark_Academia

167

Dylan Bowman

I'm an LLM evals researcher. I currently work at Apollo Research and used to work at HUD and Prof. Daniel Kang's lab.

https://x.com/Shark_Academia

Blind deep-deployment evals for control & sabotage

Thanks to Ezra Newman for initial ideation and various people at Apollo Research for feedback. This short personal piece does not necessarily reflect the views of Apollo Research. AI labs are preparing to automate their internal staff over the next year. Right now, control and sabotage evals try to estimate...

May 6•27

Goblin Mode, 24 Hours Later

Yesterday, Twitter user arb8020 posted this: It went semi-viral within AI Twitter and users began experimenting with "goblin mode" and hypothesizing about the source of the bizarre behavior. LM Arena provided evidence for the phenomenon from their traffic: > "It's true. Here's a plot of GPT models and their usage...

Apr 29•52

Dylan Bowman's Shortform

Dec 5, 2025•2