Solving the Trolley Problem
SAFETY
-
AI-Generated Misinformation: Foreign Actors Escalate Information Warfare
By
–
For four years, I tried to warn everyone that AI would radically ramp up the ability of foreign actors to generate misinformation. Now here we are.
-
Paper Shows LLM Attacks May Be Impossible
By
–
I'm confident it's impossible – have you see this paper? https://
llm-attacks.org -
Lack of Control Over Frontier AI Models Raises Safety Concerns
By
–
Personally I find the language here too anthropomorphic but the results once again highlight our deeply disconcerting lack of control over frontier models.
-
Rubrik Unveils SAGE for Intelligent AI Agent Governance
By
–
Deploying AI Agents shouldn’t leave your organization "flying blind" or stuck in manual review cycles. Join @rubrikInc on April 16th for the unveiling of SAGE (Semantic AI Governance Engine), the intelligent core powering Rubrik Agent Cloud, and start scaling innovation without sacrificing control 👉 go.rbrk.co/wco0xc
→ View original post on X — @predibase, 2026-04-01 22:09 UTC
-
Safety First: Why Simulation Overrides Matter in Industrial Systems
By
–
When it comes to simulation, there's one line you never cross: Safety. #Sponsored by SIemens.
— Lucian Fogoros (@fogoros) 1 avril 2026
Here’s why manual or simulated overrides aren't always the answer:
– Safety First: Compromising on safety is never an option, even in advanced simulations.
– Parallel Systems: Robust… pic.twitter.com/T0op20dSC1When it comes to simulation, there's one line you never cross: Safety. #Sponsored by SIemens.
Here’s why manual or simulated overrides aren't always the answer:
– Safety First: Compromising on safety is never an option, even in advanced simulations.
– Parallel Systems: Robust -
Collective Resistance: Working Together Against Technological Challenges
By
–
it’s actually up to all of us. we can resist, but only if we work together.
-
VLM Image Interpretation for Diagnosis: Reliability Concerns
By
–
Currently we use a VLM to interpret images to diagnose outcomes but that is not always reliable.
-
Accidental training data leak raises transparency questions
By
–
Accidentally leaking your own pretraining data is a bit alarming TBH. On the other hand, more transparency about training data can only be a good thing for the community.