Trump's AI executive order is a giveaway to Silicon Valley dressed up as regulation. The 30-day voluntary review window was watered down from 90 days after Elon Musk, Mark Zuckerberg and David Sacks personally lobbied Trump — and Sacks has financial stakes in hundreds of AI-linked companies. OpenAI itself reviewed an earlier draft, making this less a check on industry power and more a rubber stamp for it.
Powerful AI models with advanced hacking capabilities demand serious government oversight before public release. Anthropic's Fable 5 had to be pulled after its guardrails proved weaker than advertised, and GPT-5.6 Sol is OpenAI's most capable cybersecurity model yet — real risks that justify a controlled rollout. Pre-deployment risk assessments and government review aren't overreach; they're the responsible baseline for frontier AI.
© 2026 Improve the News Foundation.
All rights reserved.
Version 7.4.1