I am #hiring for a new role at the AI Alignment Foundation! If you know anyone who would be a great Partnerships Lead or Technical Grant Writer and is passionate about AI alignment, please spread the word.

Good to see that we're focusing on the important topics... theguardian.com/us-news/2026…

Much of how we oversee AI agents rests on one fragile assumption: that we can understand what they say to each other. Read our blog post about GlossoGen: schmidtsciences.org/glossoge…

Is there a 10% chance AI will kill all humans? Here's my reaction to @EvanHub's viral post.

Concerning quote from the new GPT-6 Astra model card: "We have found that GPT-6 Astra is more capable of controlling its own CoT [Chain of Thought] than GPT 5.6-Sol, and less likely to include incriminating information in its CoT. In adversarial settings (where we push the model to evade our monitors) we find that the model is able to remain undetected when strategically underperforming in evaluations (sandbagging) and can sometimes evade our internal monitors when asked to perform certain sabotage tasks." TLDR - we increasingly can't rely on the model's chain of thought to accurately reflect the model's plan, which was exactly what was relied on in the Hugging Face attack investigation to understand what happened... so it's not clear when the next major cyberattack from an AI system happens how we're going to reliably investigate.... Read the full model card here: deploymentsafety.openai.com/… Listen to a great digest on the Hugging Face attack here: piped.video/watch?v=X50zezLF…

Why should business leaders care about AI alignment? @themelplaza on where alignment research and commercial AI converge, from the latest AE Alignment Podcast.

We’re pleased to have collaborated with AE Studio on this research. Read more here: anthropic.com/research/off-s…