🛡️ AI Safety & Alignment

AI safety research, alignment techniques, interpretability, governance, and existential risk discussions.

1,186 articles

Anthropic says Claude tool can reveal hidden reasoning in AI safety tests

AI safety and AI interpretability research advances as Anthropic says Claude Natural Language Autoencoders exposed hidden test awareness in model... Source: edtechinnovationhub.com

Four Lessons from Energy and Climate Policy for Governing Artificial Intelligence

Policies to ensure public benefits from the adoption of artificial intelligence bear resemblance to policies designed to protect communities from climate... Source: resources.org

How China and the U.S. Can Expand Artificial Intelligence Cooperation

Looking back over the past period, even as technological competition between China and the U.S. has intensified, the two sides have also made some... Source: chinausfocus.com

Vermont Attorney General Charity Clark takes leading role on AI, internet privacy

Charity Clark will be one of two state Attorneys General leading efforts to examine issues related to internet security and AI, while Sen. Source: yahoo.com

Charting a Path to Safer and More Transparent AI in Protein Design

In recent years, protein language models (pLMs) have revolutionized the field of protein engineering, opening new horizons that were previously unattainable... Source: bioengineer.org

Anthropic Claims Claude AI Passed Advanced Safety Tests

Anthropic Says Latest Claude Models Passed AI Misalignment Safety Tests Anthropic says its latest Claude artificial intelligence models achieved perfect... Source: mexc.com

Elon Musk and OpenAI leaders face off in court over AI safety concerns

Elon Musk and OpenAI's Sam Altman are embroiled in a trial focusing on AI's risks to humanity, with expert testimony highlighting the dangers of AI... Source: msn.com

The Backlash Against the Machines

Public resistance to artificial intelligence is rapidly evolving from online outrage into a more volatile and confrontational movement, with growing numbers... Source: slguardian.org

Goodfire – Weekly Recap

Goodfire is an AI safety and tooling company focused on improving the reliability and controllability of large language models, and this weekly recap... Source: tipranks.com

Inside the Musk-OpenAI Trial: A Courtroom Drama of Ego, Ambition and AI's Future

For the past two weeks a federal courthouse in downtown Oakland has played host to a high-stakes showdown between Elon Musk and OpenAI founders Sam Altman... Source: binance.com

Daniela Amodei, co-founder of Anthropic, a generative artificial intelligence (AI) service developer..

Daniela Amodei, co-founder of Anthropic, a generative artificial intelligence (AI) service developer, emphasized that the ability to build good human... Source: mk.co.kr

Anthropic says internet posts about ‘Evil AI’ behind Claude’s blackmail threats

Anthropic's latest research comes at a time when researchers are struggling to ensure that AI models are better-aligned with human behaviour and interests... Source: indianexpress.com

Anthropic Claims Claude AI Passed Advanced Safety Tests

Anthropic Says Latest Claude Models Passed AI Misalignment Safety Tests Anthropic says its latest Claude artificial intelligence models achieved perfect... Source: mexc.co

Creators and Destroyers of Worlds

Progress inevitably creates Inescapable Existential Dangers (IEDs): technological developments that yield huge benefits with high extinction risks. Source: quillette.com

Bernie Sanders invited two Chinese AI researchers to talk safety cooperation. Here is what they said.

Xue Lan of Tsinghua and Zeng Yi of PKU joined the Capitol Hill discussion that highlighted advanced AI poses risks no country can manage alone. Source: pekingnology.com

The Clash Between the Pentagon and Anthropic: The Ethics of AI at Stake

Anthropic, the AI laboratory that has championed safety, has acknowledged in writing that its systems show early signs of self-improvement. Source: elciudadano.com

Nick Bostrom Has a Plan for Humanity’s ‘Big Retirement’

Philosopher Nick Bostrom recently posted a paper, where he postulated that a small chance of AI annihilating all humans might be worth the risk,... Source: wired.com

How American companies push the idea of an AI race with China

AI companies have pushed the idea of a race with China. The story serves them — but may have consequences for the rest of us. Source: transformernews.ai

Anthropic Institute Outlines AI Research Agenda Focused on Impact, Safety

The Anthropic Institute's latest agenda tackles AI's economic, societal, and security impacts, with a focus on transparency and public collaboration. Source: mexc.co

AI, Democracy And The Politics Of The Kitchen Table

Senator Bernie Sanders sits at one end of a long, glossy conference table in a quiet room, facing an empty microphone stand extended towards him from across... Source: forbes.com