Skip to content
View reinthal's full-sized avatar
đź’­
they should be paying ME per token
đź’­
they should be paying ME per token

Sponsoring

@natekspencer

Block or report reinthal

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
reinthal/README.md

$whoami

Hi,

I'm Alex. I'm an AI safety researcher and engineer with a taste for empirical and threat-model-driven research.

If you find any of the things I do interesting, maybe you'd like to talk? If you do, you can email me at > email at reinthal dot me < or use this link to book a meeting.


Older stuff

I used to do a lot of devops things; you can find dotfiles, infra, and older work among my repositories: github.com/reinthal?tab=repositories

Pinned Loading

  1. hackerFinder9000 hackerFinder9000 Public

    Detecting cross-context harmful requests. Placed 4th / 671, Apart D/Acc 2025

    Python 3

  2. about-emergent-misalignment about-emergent-misalignment Public

    Emergent Misalignmently misaligned or confidently incorrect? Studied if these models are too incapable to be harmful. 3rd / 8, ARENA 7.0 Capstone

    Jupyter Notebook

  3. deception-detection-in-chinese-models deception-detection-in-chinese-models Public

    Detecting Censorship, Deception and alignment problems in politically sensitive questions

    JavaScript

  4. arxiv-mcp-ng arxiv-mcp-ng Public

    Python 5 1

  5. cost-to-detection cost-to-detection Public

    HTML