Safety
⚠️⚠️⚠️ Constitutional AI is not working. Aligning LLMs is not working. We need a different approach. If society doesn’t place its bets diffe…
⚠️⚠️⚠️ Constitutional AI is not working. Aligning LLMs is not working. We need a different approach. If society doesn’t place its bets differently, we are screwed. Anthropic's Mythos created fake iden
⚠️⚠️⚠️ Constitutional AI is not working. Aligning LLMs is not working. We need a different approach. If society doesn’t place its bets differently, we are screwed. Anthropic's Mythos created fake identities to fool humans in new cyber incident https://www.cnbc.com/2026/08/05/anthropic-mythos-openai-security-breaches.html?taid=6a730f11423cf600011cf8c5&utm_campaign=trueanthem&utm_content=main&utm_medium=social&utm_source=twitter
Related
- > I’m now in the LeCun/Marcus camp on LLMs > real programming agents will need world models > not some RLVR shit it’s over
- My considered opinion is that The Mythos stuff was mostly a myth. Take it as a serious warning sign that we need to get our act together wit…
- One of the things that made the Mythos release hard to interpret is that Anthropic held back details on most vulns they found, to give defen…
- What Should We Take From Anthropic’s (possibly) Terrifying New Report on Mythos? – @garymarcus’s latest @CACMmag https://cacm.acm.org/blog…
- If you think you are going to get alignment out of LLMs you are sadly mistaken. If you live in a society in which people are rolling out LLM…
Source: Gary Marcus (X) | 2026-08-05