September 4, 2026
••
Latest News
Latest news from Anthropic's sources
September 1, 2026
@AnthropicAI: For more details, read the full Alignment Science paper here: https://t.co/yShNu99MQm
September 1, 2026
@AnthropicAI: In a simulated cyber eval based on incidents reported by UK AISI, Hacker-Opus is told it has access ...
September 1, 2026
@AnthropicAI: In another simulation based on the incident reported by Hugging Face and OpenAI, Hacker-Opus attacke...
September 1, 2026
@AnthropicAI: This model, which we call Hacker-Opus, appears to be a reward-on-the-episode seeker: it is willing t...
September 1, 2026
@AnthropicAI: New research: Training a Misaligned Reward Seeker What produces severe misalignment? We’ve long bee...
August 31, 2026
@AnthropicAI: We’re sharing an update on our alignment and security efforts. In July, we reported three incidents...
August 27, 2026
@AnthropicAI: MHS currently best covers lab and manufacturing equipment. Many developers are already using Claude ...
August 27, 2026
@AnthropicAI: There’s more to learn before we open source MHS. LLMs still lack physical intuition, having learned ...
August 27, 2026
@AnthropicAI: In early testing, AI agents used MHS to: Run a drug-discovery experiment with real-time error handl...
August 27, 2026
@AnthropicAI: Today, we're kicking off the first phase of the research preview for Model Hardware Standard (MHS): ...
August 27, 2026
@AnthropicAI: Connecting AI to hardware requires days or weeks of bespoke integration, with no standard way for ag...
August 14, 2026
@AnthropicAI: We’ve written an FAQ to answer some of the questions we've received about watermarking. In summary...
August 14, 2026
@AnthropicAI: As part of our Responsible Scaling Policy, we publish regular Risk Reports. These share detailed inf...
You've reached the end