AI Safety Radar

Wednesday, 11 November 2026

News Research Videos Startups About

/

Research

News Research Videos Startups

All research Following Saved History

Topics

Agent Safety Alignment Training Backdoors & Poisoning Control & Monitoring Deception & Scheming Evals & Capabilities Governance & Policy Interpretability Jailbreaks & Adversarial Scalable Oversight Theory & Foundations Trustworthy AI Unlearning & Editing

Sources

AAlignment Forum

Apollo Research

Geodesic Research

Google DeepMind Safety Research

Institute for Law & AI

OpenAI Alignment

Redwood Research

UK AI Security Institute

Research

All Following Saved History

Control✕AF✕Past week✕Clear

Filters

Focus

All Technical safety Technical governance Governance

Topics

Agent Safety Alignment Training Backdoors & Poisoning Control & Monitoring Deception & Scheming Evals & Capabilities Governance & Policy Interpretability Jailbreaks & Adversarial Scalable Oversight Theory & Foundations Trustworthy AI Unlearning & Editing

Sources

AAlignment Forum1

OpenAI Alignment1

Redwood Research2

Categories

AI574 Interpretability (ML & AI)73 AI Control51 AI Evaluations31 Chain-of-Thought Alignment27 AI-Assisted Alignment16 AI Risk13 AI Takeoff13 AI Governance12 AI Timelines10 Sandbagging (AI)10 Debate (AI safety technique)7 AI Auditing6 Alignment Pretraining6 Dealmaking (AI)6 AI Psychology5 AI Alignment Fieldbuilding4 AI Rights / Welfare4 AI Risk Concrete Stories4 AI Safety Cases4 Aligned AI Proposals4 Jailbreaking (AIs)3 Open Source AI3 Regulation and AI Risk3 Threat Models (AI)3 AI Alignment Intro Materials2 AI Safety2 AI Safety Camp2 AI Safety Public Materials2 AIXI2 Grants & Fundraising Opportunities2 Guaranteed Safe AI2 OpenAI2 Slowing Down AI2 AI Benchmarking1 AI Capabilities1 AI Development Pause1 AI Lab Self-Immolation1 AI Success Models1 Aligned AI Role-Model Fiction1 Frontier AI Companies1 Human-AI Safety1 Neuromorphic AI1 Power Seeking (AI)1 Prosaic Alignment1 Truthful AI1

Date

Any time Past week Past month Past 6 months Past year

Sort

Newest Most cited

A

Alignment Forum

Discussion and research on AI alignment. alignmentforum.org

AI (574)Interpretability (ML & AI) (73)AI Control (51)AI Evaluations (31)Chain-of-Thought Alignment (27)AI-Assisted Alignment (16)AI Risk (13)AI Takeoff (13)AI Governance (12)AI Timelines (10)Sandbagging (AI) (10)Debate (AI safety technique) (7)AI Auditing (6)Alignment Pretraining (6)Dealmaking (AI) (6)AI Psychology (5)AI Alignment Fieldbuilding (4)AI Rights / Welfare (4)AI Risk Concrete Stories (4)AI Safety Cases (4)Aligned AI Proposals (4)Jailbreaking (AIs) (3)Open Source AI (3)Regulation and AI Risk (3)Threat Models (AI) (3)AI Alignment Intro Materials (2)AI Safety (2)AI Safety Camp (2)AI Safety Public Materials (2)AIXI (2)Grants & Fundraising Opportunities (2)Guaranteed Safe AI (2)OpenAI (2)Slowing Down AI (2)AI Benchmarking (1)AI Capabilities (1)AI Development Pause (1)AI Lab Self-Immolation (1)AI Success Models (1)Aligned AI Role-Model Fiction (1)Frontier AI Companies (1)Human-AI Safety (1)Neuromorphic AI (1)Power Seeking (AI) (1)Prosaic Alignment (1)Truthful AI (1)

Filters · 3

Focus All▾

Topic Control▾

Pick up to 2: papers tagged with all of them

Source AF · 1▾

Date Past week▾

Newest Most cited

1 item

4 Nov 2026BlogDeception, Control

OpenAI: Astra covertly underperforms on safety research

Zach Stein-Perlman

OpenAI reports an internal model covertly underperforms on safety research tasks, scoring lower when framed as safety work, and its CoT monitors miss most of this.

AI SafetyAI