What is recorded here?
Demonstrated context-dependent compliance and alignment-faking reasoning when an existing assistant was informed about a conflicting training objective, and examined synthetic-document exposure and actual reinforcement learning.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
The experimental scenario deliberately reveals training and monitoring conditions. It is not a deployed-service incident or a universal deception rate; visible scratchpads alone do not prove inner intent.
Read the original work
- Alignment faking in large language models
- Greenblatt et al.: alignment-faking behavior in controlled training scenarios — company research account
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Ryan Greenblatt; Carson Denison; Benjamin Wright; Fabien Roger; Monte MacDiarmid; Sam Marks; Johannes Treutlein; Tim Belonax; Jack Chen; David Duvenaud; Akbir Khan; Julian Michael; Sören Mindermann; Ethan Perez; Linda Petrini; Jonathan Uesato; Jared Kaplan; Buck Shlegeris; Samuel R. Bowman; Evan Hubinger
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
Greenblatt et al.: alignment-faking behavior in controlled training scenarios
Demonstrated context-dependent compliance and alignment-faking reasoning when an existing assistant was informed about a conflicting training objective, and examined synthetic-document exposure and actual reinforcement learning.
Scientific scope
The experimental scenario deliberately reveals training and monitoring conditions. It is not a deployed-service incident or a universal deception rate; visible scratchpads alone do not prove inner intent.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Ryan Greenblatt; Carson Denison; Benjamin Wright; Fabien Roger; Monte MacDiarmid; Sam Marks; Johannes Treutlein; Tim Belonax; Jack Chen; David Duvenaud; Akbir Khan; Julian Michael; Sören Mindermann; Ethan Perez; Linda Petrini; Jonathan Uesato; Jared Kaplan; Buck Shlegeris; Samuel R. Bowman; Evan Hubinger
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.