Skip to content Longterm Wiki has not been actively maintained since May 2026. Some data is still updated occasionally, but please don't rely on this site being current or accurate.
Organizations / Redwood Research
Name DivisionType Status Source Notes Source check Redwood Research team active redwoodresearch.org Core 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. Not checked
Dimension Rating Evidence Assessor Source check focus-area AI systems acting against developer interests Primary research on AI Control and alignment faking editorial Not checked funding $25M+ from Coefficient Giving $9.4M (2021), $10.7M (2022), $5.3M (2023) editorial Not checked key-concern Research output relative to funding 2023 critics cited limited publications; subsequent ICML, NeurIPS work addressed this editorial Not checked team-size 10 staff (2021), 6-15 research staff (2023 estimate) Early team of 10 expanded to research organization editorial Not checked
Title Date EventType Description Significance Source Source check Alignment faking paper with Anthropic 2024-12 publication Landmark collaboration with Anthropic on alignment faking research. major anthropic.com Not checked Buck Shlegeris becomes CEO; AI Control ICML oral 2024 leadership-change Buck Shlegeris transitions from CTO to CEO and Director; Ryan Greenblatt serves as Chief Scientist. AI Control work accepted as an ICML oral. major projects.propublica.org Not checked REMIX interpretability program runs 2023 launch Mechanistic interpretability training program for ~10-15 junior researchers. moderate forum.effectivealtruism.org Not checked Adversarial robustness research project 2022 milestone Initial adversarial training project; later acknowledged by leadership as unsuccessful. minor blog.redwoodresearch.org Not checked Causal scrubbing methodology developed 2022 publication Developed across 2022-2023; method for rigorously testing mechanistic interpretability claims. moderate lesswrong.com Not checked MLAB bootcamp launches 2021-12 launch Inaugural ML for Alignment Bootcamp with 40 participants; 3-week intensive teaching attendees to build BERT/GPT-2 from scratch. moderate blog.redwoodresearch.org Not checked Tax-exempt status granted; 10 staff assembled 2021-09 founding — major projects.propublica.org Not checked
▶ Internal MetadataID: 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