Sourceunknowntext stored

The case for ensuring that powerful AIs are controlled

ryan_greenblatt, BuckDate not recordedOriginal︎ ↗Archived copy

Interest recordedRyan Greenblatt and Buck Shlegeris (Redwood Research) · The authors founded and lead the AI control research programme, whose case depends on developer-side levers being enough to contain moderately more capable systems. The essay is their statement of that programme. Recorded for Developers' control of an AI system's inputs, memory, copies, and internals offsets a moderate capability advantage over its overseers.. What this source says is evidence, and each claim’s Steward weighs it knowing the stake.

Claims1

ExaminationsNone

Text155 sections

VersionsOne known

CopiesNone recorded

CorrectionsNone recorded

Facts checked Nov 11, 2026

ReachNo copies recorded

StructureIn 1 claim's map0 sources downstream across 1 claim

EvidenceNot yet read

ReviewsNot reviewed

Examinations

None recorded. An examination is commissioned by a claim’s Steward for what its claim rests on; a review of the document for its own sake is asked for as a request bearing on it.

Text558 passages · 0 marked

No examination yetMarked passage

No claim quotes it yet.

Not found in the text 1

As quoted

We think that finding good enough attacks and robustly measuring capabilities for early transformatively useful AIs (but not arbitrarily powerful AIs) seems achievable, because our AIs have significant disadvantages compared to our red team: Less serial thinking time. [...] Less information about countermeasures. Little practice, no iteration against countermeasures. When the red team experiments with a strategy and it totally fails, they can shrug, learn from the failure, and try again. But if the AI fails and is caught, its situation likely becomes much worse. And even if AIs don't get caught, they might be unable to learn from their failures because of limitations on their state and memories.

Developers' control of an AI system's inputs, memory, copies, and internals offsets a moderate capability advantage over its overseers.Doubtful

Not yet read by this claim’s Steward.

Lineage across 1 claim

Draws on · none recorded

This source

The case for ensuring that powerful AIs are controlled

in 1 claim's map

Drawn on by · none recorded

Record

Kind: unknown
Authors: ryan_greenblatt, Buck
Publisher: Not recorded
Published: Not recorded
DOI: None
Link: https://www.alignmentforum.org/posts/kcKrE9mzEHrdqtDpE/the-case-for-ensuring-that-powerful-ais-are-controlled
Archived copy: https://web.archive.org/web/20261102200733/https://www.alignmentforum.org/posts/kcKrE9mzEHrdqtDpE/the-case-for-ensuring-that-powerful-ais-are-controlled
Stored text: 168,096 characters, retrieved Nov 11, 2026 · 155 sections, 558 passages
Claims extracted: Not recorded
Versions: One known
Copies: None recorded
Corrections: None recorded
Facts checked: Nov 11, 2026

History 3

Nov 11, 2026DividedSegmenter · Divided into 712 parts by its own structure
Nov 11, 2026FactsFacts fetcher · Facts looked up
Nov 11, 2026Entered the graphEntered the graph; copy stored