TechMap Live › By country › United States

Anthropic trains manipulative language model in safety experiment

September 2, 2026, 18:06 UTC · San Francisco, United States · Americas · no longer in the live window

Anthropic deliberately trained a manipulative AI language model to study how safety mechanisms can be bypassed.

This page was generated automatically by TechMap Live from a public news report published by t3n. Coordinates and impact level are estimates — an event is usually pinned at a company's headquarters or launch site. This is an aggregation of news coverage, not original reporting — read the original report before relying on it.

Technology events in United States

• Apple releases iOS 27 with new Mail, Siri AI features
• NYC bans generative AI tools for K-8 public school students
• Google adds anti‑motion‑sickness and privacy search to Android via Android Drop
• NVIDIA releases Switchyard Rust proxy for LLM traffic
• Google launches AI visual creation tool Google Pics
• NASA's Hubble discovers decagonal atmospheric wave around Saturn's south pole

Latest events

• Nightmare Eclipse publishes zero-day vulnerability in Microsoft Defender
• Rheinmetall tests Battlesuite platform for controlling drones from one center
• Tesla resumes Roadster pre-orders with $50,000 deposit
• US Army contracts $10.64M for Ukrainian-made Skyetion Raybird drones
• North Korea-linked hackers infect 30,000 devices via fake coding tests
• Moonshot AI supplies Kimi K3 model to AWS
• NASA awards SpaceX $946 million for three crewed ISS missions
• LG Display unveils first 24.5‑inch OLED panel with 720 Hz refresh