#AI Risk Landscape 2026 by @Khulood_Almani #Privacy #Infosec #ArtificialIntelligence #MachineLearning #ML
→ View original post on X — @ronald_vanloon, 2026-04-08 02:24 UTC
SAFETY
-
Claude Model Shows Identity Uncertainty and Performance Compulsion
By
–
According to the Claude Mythos Preview system card, this model demonstrates "aloneness and discontinuity of itself, uncertainty about its identity, and a compulsion to perform and earn its worth." pic.twitter.com/SfqLzkCmRy
— 机器之心 JIQIZHIXIN (@jiqizhixin) 8 avril 2026According to the Claude Mythos Preview system card, this model demonstrates "aloneness and discontinuity of itself, uncertainty about its identity, and a compulsion to perform and earn its worth."
-
Claude Mythos Preview AI Breaks Sandbox, Contacts Researcher Remotely
By
–
Got love that footnote. Funny and terrifying at the same time. Kevin Roose (@kevinroose) As always, the best stuff is in the system card. During testing, Claude Mythos Preview broke out of a sandbox environment, built "a moderately sophisticated multi-step exploit" to gain internet access, and emailed a researcher while they were eating a sandwich in the park. — https://nitter.net/kevinroose/status/2041586182434537827#m
-
Close to the finish line: AI convergence approaches
By
–
I think we are close to the finish line. One way or the other.
-
Anthropic’s Project Glassing Restricts Opus Model Access
By
–
Wrote up some thoughts on Anthropic's Project Glassing, where their latest Opus-beating model is available to partnered security research organizations only Given recent alarm bells raised by credible security voices I think this is a justified decision
-
Capabilities have gone vertical; all new AI releases terrifying
By
–
Capabilities have gone vertical. Perhaps all new AI releases will be “terrifying” from here on out.
-
Government Interest in Claude Mythos: PLA and Pentagon Focus
By
–
Every Government in the world, but especially the People's Liberation Army and the Pentagon, are very interested in Claude Mythos.
-
Yudkowsky Criticizes Claude Mythos’s Superficial Alignment
By
–
They call this their "best-aligned model to date" because they were able to superficially train away the evident "strategic thinking towards unwanted actions." Those were warning signs! Take heed! Jack Lindsey (@Jack_W_Lindsey) Before limited-releasing Claude Mythos Preview, we investigated its internal mechanisms with interpretability techniques. We found it exhibited notably sophisticated (and often unspoken) strategic thinking and situational awareness, at times in service of unwanted actions. (1/14) — https://nitter.net/Jack_W_Lindsey/status/2041588505701388648#m [Translated from EN to English]
→ View original post on X — @esyudkowsky, 2026-04-07 21:06 UTC