Skip to content
Longterm Wiki

Redwood Research

Safety Organization
Founded Jun 2021 (4 years old)HQ: San Francisco, CAredwoodresearch.org

Also known as: Redwood

Structured Facts
Database Records
Revenue
$22K
as of 2024
Headcount
34
as of 2023
Founded Date
Jun 2021

All Facts

Financial

Annual Expenses$2.9M20244 pts
As OfValueLink
2024$2.9Mview →
2023$13Mview →
2022$13Mview →
2021$2.3Mview →
Headcount3420232 pts
As OfValueLink
202334view →
Oct 202110view →
Net Assets$6.5M20244 pts
As OfValueLink
2024$6.5Mview →
2023$8.3Mview →
2022$11Mview →
2021$12Mview →
Revenue$22K20244 pts
As OfValueLink
2024$22Kview →
2023$10Mview →
2022$12Mview →
2021$14Mview →

Organization

Founded DateJun 2021view →
HeadquartersSan Francisco, CAview →

People

Other

Divisions

1
NameDivisionTypeStatusSourceNotesSource check
Redwood Researchteamactiveredwoodresearch.orgCore research team working on interpretability and adversarial training techniques. Small org (~15-20 people) focused on applied alignment research including causal scrubbing and circuit-level interpretability.

Entity Assessments

4
DimensionRatingEvidenceAssessorSource check
focus-areaAI systems acting against developer interestsPrimary research on AI Control and alignment fakingeditorial
funding$25M+ from Coefficient Giving$9.4M (2021), $10.7M (2022), $5.3M (2023)editorial
key-concernResearch output relative to funding2023 critics cited limited publications; subsequent ICML, NeurIPS work addressed thiseditorial
team-size10 staff (2021), 6-15 research staff (2023 estimate)Early team of 10 expanded to research organizationeditorial

Entity Events

7
TitleDateEventTypeDescriptionSignificanceSourceSource check
Alignment faking paper with Anthropic2024-12publicationLandmark collaboration with Anthropic on alignment faking research.majoranthropic.com
Buck Shlegeris becomes CEO; AI Control ICML oral2024leadership-changeBuck Shlegeris transitions from CTO to CEO and Director; Ryan Greenblatt serves as Chief Scientist. AI Control work accepted as an ICML oral.majorprojects.propublica.org
REMIX interpretability program runs2023launchMechanistic interpretability training program for ~10-15 junior researchers.moderateforum.effectivealtruism.org
Adversarial robustness research project2022milestoneInitial adversarial training project; later acknowledged by leadership as unsuccessful.minorblog.redwoodresearch.org
Causal scrubbing methodology developed2022publicationDeveloped across 2022-2023; method for rigorously testing mechanistic interpretability claims.moderatelesswrong.com
MLAB bootcamp launches2021-12launchInaugural ML for Alignment Bootcamp with 40 participants; 3-week intensive teaching attendees to build BERT/GPT-2 from scratch.moderateblog.redwoodresearch.org
Tax-exempt status granted; 10 staff assembled2021-09foundingmajorprojects.propublica.org
Internal Metadata
ID: sid_dwMzc9WzPa
Stable ID: sid_dwMzc9WzPa
Wiki ID: E557
Type: organization
YAML Source: packages/factbase/data/fb-entities/redwood-research.yaml
Facts: 19 structured
Records: 12 in 3 collections