Skip to content
View tylercrosse's full-sized avatar
32 followers · 23 following

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Block or report tylercrosse

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
tylercrosse/README.md

👋 Hi, I'm Tyler

I'm a research engineer focused on interpretability and ML infrastructure. Currently finishing my MSCS at Georgia Tech (ML & Computing Systems) while doing alignment research with SPAR and MARS. Previously a Senior SWE & Team Lead for 7 years. My work spans mechanistic interpretability, GPU systems, and building tooling that makes safety research possible at scale.


📄 Writing & Analysis

🔗 Links

Pinned Loading

  1. mars-attacks mars-attacks Public

    Dynamic Attack Selection in Agentic AI Control Evaluations

    Python 1

  2. LLM_morality LLM_morality Public

    Forked from liza-tennant/LLM_morality

    Building off of Liza Tennant's Moral Alignment for LLM Agents

    Python

  3. goal-drift-gym goal-drift-gym Public

    Harness for measuring and analyzing goal drift in multi-step decision-making agents.

    Python

  4. goal-drift-evals goal-drift-evals Public

    Forked from RaunoArike/goal-drift-evals

    Fork of Rauno Arike's work

    Python

  5. rl-algs rl-algs Public

    RL Safety Reward Misspecification Benchmarks

    Python

  6. personal-site personal-site Public

    HTML