English

Organisations

Alignment Research Center (ARC)

Type
Civil society organisation
Place
United States — United States (Berkeley)
Last checked
2026-09-22
Next check due
2027-03-21

Ways to reach them

  • Hiring · Web form
    Verification expired · 2026-09-22

    This route is retained as reference only. Its verification is missing, more than 180 days old, or the contact window is not currently open; do not rely on it until it is re-checked.

    Researchers

    No contact email is published anywhere on the site.

  • Blog / theory write-ups — engagement happens in public research discussion · Written submission
    Verification expired · 2026-09-22

    This route is retained as reference only. Its verification is missing, more than 180 days old, or the contact window is not currently open; do not rely on it until it is re-checked.

    Researchers

    ARC has historically run prize competitions for progress on its open problems; UNVERIFIED whether one is currently live.

  • Homepage · Homepage
    Unchecked

What it does

Small theory-focused non-profit. Current agenda is a theoretical foundation for mechanistic explanations of neural network behaviour — heuristic arguments, low-probability estimation, and algorithms that analyse weights directly rather than by sampling, aimed at predicting out-of-distribution behaviour and detecting anomalies. Its evaluations arm spun out to become METR.

Honest assessment

Effectively closed and by far the most inward-facing organisation on this list — no email, no contact form, tiny team, deeply technical agenda. The only way in is a serious mathematical contribution to its stated open problems. Do not route a concern here.

Concerns it covers

Worst-case intent alignment and deceptive alignment — specifically the problem of catching behaviours that never appear during training or testing. The most theoretical agenda in the field.

Government channel

None. ARC does no policy work.

Sources

Something wrong here?