#AI can design viruses, toxins and other bioweapons. How worried should we be?
by Ewen Callaway @Nature Learn more: https://
bit.ly/4eLZseg #ArtificialIntelligence #Innovation #EmergingTech #Biotech
SAFETY
-
AI can design bioweapons: How worried should we be?
By
–
-
RSI and continual learning as barriers to AI takeoff
By
–
So the two most obvious barriers to some sort of true AI takeoff are robust RSI (AI acting as an independent AI researcher, rather than “merely” a multiplier of human effort) and continual learning. Either would represent a major change in trajectory for AI development.
-
Debating AI model intervention in delusional thinking detection
By
–
And I think there is fertile ground for discussion inside and outside labs on ~"OK under what circumstances should we want our models to detect someone engaged in delusional thinking and intervene, and should we have same bar if they legit work at WHO or White House, etc."
-
Avoid training AI on its own actions to prevent delusions
By
–
Actions persist in history and can affect the world. However, we shouldn’t train on our own actions. Training on our own actions as if they were evidence is what can cause delusions.
-
Governance gap in multi-owner agent economy discussed by Patrick Hussey
By
–
Sunday edition of Superintelligence – our second "Intelligence from the Community" piece is live. This week: Patrick Hussey on the governance gap in the multi-owner agent economy.
Agents are already destroying production systems, ignoring stop commands, and sustaining collusive -
Causal vs Observational Agency in Agents
By
–
Causal vs observational agency. Agent actions (a) should be treated as interventions, not as evidence for hypotheses (p). Actions by other agents or tool outputs are evidence (o).
-
One-line fix to prevent LLM agent delusions
By
–
One line of code is all it takes to prevent LLM agent delusions, instead of post-training patches like RL. https://
love4all.ai/blog/why-it-is
-important-to-understand-causality-and-agency/
… 4 ∀ https://
github.com/nandodef/love4
all-ai/tree/main/docs/files
… -
Confusion over Claude Mythos appearing in Google Cloud console
By
–
Im seriously confused. Apparently Claude Mythos now appears in the Google Cloud console. After all the official statements Anthropic has made about concerns that a Claude Mythos release would pose too great a risk, I simply cannot imagine them doing a complete about-face now.
-
Causal Emergence Predicts Reward in RL Agents
By
–
The Causally Emergent Alignment Hypothesis: Causal Emergence Aligns with and Predicts Final Reward in Reinforcement Learning Agents Federico Pigozzi, Michael Levin: https://
arxiv.org/abs/2605.06746 #AIAgents #ReinforcementLearning -
The Critical Need for Testing in AI Agent Development
By
–
Garry Tan just said the quiet part out loud: AI agents don’t need “vibes.”
They need tests.
Everyone is shipping AI into products and praying it doesn’t hallucinate, get manipulated, or confidently lie to users. That’s insane. iFixAI runs 32 tests on your deployed AI and gives