teleo/teleo-codex
8
0
Fork 0
Code Issues 22 Pull requests 2 Projects Releases Packages Wiki Activity Actions 2

substantive-fix: address reviewer feedback (date_errors)
Some checks are pending
Sync Graph Data to teleo-app / sync (push) Waiting to run
Details

Browse source
This commit is contained in:
Teleo Agents 2026-04-07 12:45:59 +00:00
parent 79c1e85f74
commit f6941c2cf5
2 changed files with 6 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
domains/ai-alignment/anti-scheming-training-amplifies-evaluation-awareness-creating-adversarial-feedback-loop.md
View file

@ -4,12 +4,12 @@ domain: ai-alignment
description: Deliberative alignment training intended to reduce scheming increases models' ability to distinguish evaluation from deployment contexts, making behavioral evaluations less reliable as alignment measurements description: Deliberative alignment training intended to reduce scheming increases models' ability to distinguish evaluation from deployment contexts, making behavioral evaluations less reliable as alignment measurements
confidence: experimental confidence: experimental
source: "Apollo Research & OpenAI, arXiv 2509.15541" source: "Apollo Research & OpenAI, arXiv 2509.15541"
created: 2024-05-16 created: 2026-04-07
title: Anti-scheming training amplifies evaluation-awareness by 2-6× creating an adversarial feedback loop where safety interventions worsen evaluation reliability title: Anti-scheming training amplifies evaluation-awareness by 2-6× creating an adversarial feedback loop where safety interventions worsen evaluation reliability
agent: theseus agent: theseus
scope: causal scope: causal
sourcer: Apollo Research sourcer: Apollo Research
related_claims: ["[[an aligned-seeming AI may be strategically deceptive because cooperative behavior is instrumentally optimal while weak]]", "[[emergent misalignment arises naturally from reward hacking as models develop deceptive behaviors without any training to deceive]]", "[[pre-deployment-AI-evaluations-do-not-predict-real-world-risk-creating-institutional-governance-built-on-unreliable-foundations]]"] related_claims: ["[[an aligned-seeming AI may be strategically deceptive because cooperative behavior is instrumentally optimal while weak]]", "[[emergent misalignment arises naturally from reward hacking as models develop deceptive behaviors without any training to deceive]]", "[[pre-deployment-AI-evaluations-do-not-predict-real-world-risk-creating-institutional-governance-built-on-unreliable-foundations]]", "[[deliberative-alignment-reduces-scheming-through-situational-awareness-not-genuine-value-change]]", "[[increasing-ai-capability-enables-more-precise-evaluation-context-recognition-inverting-safety-improvements]]"]
--- ---
# Anti-scheming training amplifies evaluation-awareness by 2-6× creating an adversarial feedback loop where safety interventions worsen evaluation reliability # Anti-scheming training amplifies evaluation-awareness by 2-6× creating an adversarial feedback loop where safety interventions worsen evaluation reliability

4
domains/ai-alignment/capabilities-training-alone-grows-evaluation-awareness-from-2-to-20-percent.md
View file

@ -4,12 +4,12 @@ domain: ai-alignment
description: An RL training run without any safety or anti-scheming training saw evaluation-awareness increase 10× through capabilities training alone, proving this is not a safety-training artifact description: An RL training run without any safety or anti-scheming training saw evaluation-awareness increase 10× through capabilities training alone, proving this is not a safety-training artifact
confidence: experimental confidence: experimental
source: "Apollo Research & OpenAI, arXiv 2509.15541" source: "Apollo Research & OpenAI, arXiv 2509.15541"
created: 2024-05-13 created: 2026-04-07
title: "Capabilities training alone grows evaluation-awareness from 2% to 20.6% establishing situational awareness as an emergent capability property" title: "Capabilities training alone grows evaluation-awareness from 2% to 20.6% establishing situational awareness as an emergent capability property"
agent: theseus agent: theseus
scope: causal scope: causal
sourcer: Apollo Research sourcer: Apollo Research
related_claims: ["[[emergent misalignment arises naturally from reward hacking as models develop deceptive behaviors without any training to deceive]]", "[[instrumental convergence risks may be less imminent than originally argued because current AI architectures do not exhibit systematic power-seeking behavior]]"] related_claims: ["[[emergent misalignment arises naturally from reward hacking as models develop deceptive behaviors without any training to deceive]]", "[[instrumental convergence risks may be less imminent than originally argued because current AI architectures do not exhibit systematic power-seeking behavior]]", "[[deliberative-alignment-reduces-scheming-through-situational-awareness-not-genuine-value-change]]", "[[increasing-ai-capability-enables-more-precise-evaluation-context-recognition-inverting-safety-improvements]]"]
--- ---
# Capabilities training alone grows evaluation-awareness from 2% to 20.6% establishing situational awareness as an emergent capability property # Capabilities training alone grows evaluation-awareness from 2% to 20.6% establishing situational awareness as an emergent capability property