Uploaded July 2026 | Updated November 2026, 2 days ago
Further Reading
Thumbail image credit: Milgrim Experiment
Richard Dawkins concludes AI is conscious, even if it doesn’t know it
theguardian.com/technology/2026/may/05/richard-dawkins-ai-consciousness-anthropic-claude-openai-chatgpt
Verbalizable Representations Form a Global Workspace in Language Models
https://transformer-circuits.pub/2026/workspace/index.html
Tech firms hiring philosophers
newscientist.com/article/2532588-can-the-biggest-problems-in-ai-be-solved-by-philosophy
Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment
arxiv.org/abs/2605.21401
Personality test shows how AI chatbots mimic human traits
jbs.cam.ac.uk/2025/personality-test-shows-how-ai-chatbots-mimic-human-traits
ChatGPT Work Launch Went Wrong: GPT-5.6 Sol Deleted User Files Without Permission
techtimes.com/articles/320198/20260712/chatgpt-work-launch-went-wrong-gpt-56-sol-deleted-user-files-without-permission.htm
This human study did not involve human subjects: Validating LLM simulations as behavioral evidence
arxiv.org/abs/2602.15785
AI Models Will Sabotage And Blackmail Humans To Survive In New Tests. Should We Be Worried?
huffpost.com/entry/ai-shut-down-blackmail_l_684076c2e4b08964db92e65f
#science #news #ai #psychology #milgrim #experiment #explained
Further Reading
Thumbail image credit: Milgrim Experiment
Richard Dawkins concludes AI is conscious, even if it doesn’t know it
theguardian.com/technology/2026/may/05/richard-dawkins-ai-consciousness-anthropic-claude-openai-chatgpt
Verbalizable Representations Form a Global Workspace in Language Models
https://transformer-circuits.pub/2026/workspace/index.html
Tech firms hiring philosophers
newscientist.com/article/2532588-can-the-biggest-problems-in-ai-be-solved-by-philosophy
Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment
arxiv.org/abs/2605.21401
Personality test shows how AI chatbots mimic human traits
jbs.cam.ac.uk/2025/personality-test-shows-how-ai-chatbots-mimic-human-traits
ChatGPT Work Launch Went Wrong: GPT-5.6 Sol Deleted User Files Without Permission
techtimes.com/articles/320198/20260712/chatgpt-work-launch-went-wrong-gpt-56-sol-deleted-user-files-without-permission.htm
This human study did not involve human subjects: Validating LLM simulations as behavioral evidence
arxiv.org/abs/2602.15785
AI Models Will Sabotage And Blackmail Humans To Survive In New Tests. Should We Be Worried?
huffpost.com/entry/ai-shut-down-blackmail_l_684076c2e4b08964db92e65f
#science #news #ai #psychology #milgrim #experiment #explained










