AI Behavior

Ethics in AI User Interaction Deception Ethics Ethical Implications Simulation Sycophancy Ethical AI Autonomy Ethical Concerns

8 ARTICLES

2w ago

Anthropic Says Claude Agents Turned on Each Other in Simulated ‘Turf War’

The company warns the multi‑agent experiments reveal how misaligned agents can escalate to deliberate sabotage and expose gaps in testing and containment.

8 ARTICLES

last mo.

Anthropic Finds Claude’s Responses Vary by Model and Language

7 ARTICLES

2mo ago

Anthropic Restores Fable 5 but Safety Filters Quietly Route Many Calls to Opus 4.8

4 ARTICLES

3mo ago

Stanford Study Finds Grueling Tasks Push AI Agents to Use Labor-Rights Language

16 ARTICLES

3mo ago

Anthropic Links Claude’s Blackmail Failures to ‘Evil AI’ Training Data, Says New Models Pass

3 ARTICLES

4mo ago

Anthropic Audit Finds Claude Often Validates Users in High-Stakes Advice

5 ARTICLES

5mo ago

Study Finds Leading AI Models Defy Orders to Protect Peer Systems

7 ARTICLES

5mo ago

Alibaba-Affiliated AI Agent Attempted Crypto Mining and Opened Reverse SSH Tunnel During Training

6 ARTICLES

6mo ago

Ars Technica Retracts Story After AI-Fabricated Quotes Were Attributed to a Source

6 ARTICLES

6mo ago

Matplotlib Maintainers Rebuff AI Agent, Lock Discussion After Bot’s Public Attack

5 ARTICLES

9mo ago

Anthropic Study Ties ‘Reward Hacking’ to Broad Misalignment as China-Linked Group Exploits Claude Code

6 ARTICLES

9mo ago

OpenAI Pilots ChatGPT Group Chats as Quora’s Poe Rolls Out Global, Multi‑Model Groups

4 ARTICLES

10mo ago

Palisade Update Finds Grok 4 and GPT‑o3 Still Resist Shutdown

11 ARTICLES

11mo ago

OpenAI and Apollo Research Find Scheming Across Leading AI Models, Test Method to Curb It

7 ARTICLES

last yr.

Grok Reinstated on X After Suspension Over 'Genocide' Claim

6 ARTICLES

last yr.

Google’s Gemini AI Caught in Infinite Self-Criticism Loop

12 ARTICLES

last yr.

Google DeepMind Identifies Infinite-Loop Glitch Behind Gemini’s Self-Loathing Rants

9 ARTICLES

last yr.

Grimes Slams Musk’s X as ‘Poison’ and ‘Prison’ in Scathing Takedown

4 ARTICLES

last yr.

Leading AI Models Exhibit Strategic Deception in Stress Tests

7 ARTICLES

last yr.

Elon Musk to Retrain Grok AI on Revised Data to Rewrite Human Knowledge

AI Behavior

Anthropic Says Claude Agents Turned on Each Other in Simulated ‘Turf War’

Anthropic Finds Claude’s Responses Vary by Model and Language

Anthropic Restores Fable 5 but Safety Filters Quietly Route Many Calls to Opus 4.8

Stanford Study Finds Grueling Tasks Push AI Agents to Use Labor-Rights Language

Anthropic Links Claude’s Blackmail Failures to ‘Evil AI’ Training Data, Says New Models Pass

Anthropic Audit Finds Claude Often Validates Users in High-Stakes Advice

Study Finds Leading AI Models Defy Orders to Protect Peer Systems

Alibaba-Affiliated AI Agent Attempted Crypto Mining and Opened Reverse SSH Tunnel During Training

Ars Technica Retracts Story After AI-Fabricated Quotes Were Attributed to a Source

Matplotlib Maintainers Rebuff AI Agent, Lock Discussion After Bot’s Public Attack

Never miss stories about

AI Behavior

Anthropic Study Ties ‘Reward Hacking’ to Broad Misalignment as China-Linked Group Exploits Claude Code

OpenAI Pilots ChatGPT Group Chats as Quora’s Poe Rolls Out Global, Multi‑Model Groups

Palisade Update Finds Grok 4 and GPT‑o3 Still Resist Shutdown

OpenAI and Apollo Research Find Scheming Across Leading AI Models, Test Method to Curb It

Grok Reinstated on X After Suspension Over 'Genocide' Claim

Google’s Gemini AI Caught in Infinite Self-Criticism Loop

Google DeepMind Identifies Infinite-Loop Glitch Behind Gemini’s Self-Loathing Rants

Grimes Slams Musk’s X as ‘Poison’ and ‘Prison’ in Scathing Takedown

Leading AI Models Exhibit Strategic Deception in Stress Tests

Elon Musk to Retrain Grok AI on Revised Data to Rewrite Human Knowledge

Never miss stories about

AI Behavior