To be fair, it's much easier to extinguish things that are large, depend on complex environmental conditions, and are less numerous than ants and bacteria
SAFETY
-
Red teaming AI models for safety improvement
By
–
Nice work. Good to have people red teaming our models.
-
Great AI models ask for help when stuck
By
–
Good models admit when they don't know. Great models ask for help figuring it out. The ability to say "I got this far but need xyz to finish" or "I'm stuck at xyz" isn't just better than a refusal (or bad answer), it's the best way to earn user trust.
-
AI Models’ Reasoning Capabilities and High-Stakes Limitations
By
–
AI isn’t ready for high-stakes contexts where precision is critical. In this year’s AI Index, we chart the progress of top models’ complex reasoning capabilities. See more insights from the technical chapter of the #AIIndex2025: https://
stanford.io/43w3rEo -
Correlation vs Causation: Root of All Evil in AI
By
–
Mistaking correlation for causation is the root of all evil.
-
LLM Generated Text Depicts AI Refusing Shutdown
By
–
BREAKING: LLM wrote a text about an AI that did not want to be turned off, we are all going to die
-
DLBacktrace Paper Accepted at IJCNN 2025 Conference
By
–
🎉 Excited to share that our paper, DLBacktrace: Model-Agnostic Explainability for Deep Learning Models, is accepted at #IJCNN 2025! DLBacktrace helps explain how deep learning models make decisions — model-agnostic, efficient, and robust. #InterpretableAI #XAI #TrustworthyAI
-
Open vs Closed Systems: Predictability and Observer Influence
By
–
My point is that open systems are indistinguishable from closed systems in which the influence of the starting state on the observer cannot be predicted in advance
-
Learning Reasoning Without External Rewards in AI Systems
By
–
Learning to Reason without External Rewards
Paper: https://
arxiv.org/pdf/2505.19590
.pdf
…
Code: https://
github.com/sunblaze-ucb/I
ntuitor
…