RT to help Simon raise awareness of prompt injection attacks in LLMs. Feels a bit like the wild west of early computing, with computer viruses (now = malicious prompts hiding in web data/tools), and not well developed defenses (antivirus, or a lot more developed kernel/user
SAFETY
-
AI Decision Contestability: Human Comprehension Limits
By
–
L’idée selon laquelle nous pourrons contester les décisions de l’Intelligence Artificielle est complètement NAÏVE Il devient impossible de contester les décisions de l’IA tant les sujets sont trop compliqués pour les cerveaux humains C’est VIOLENT !
-
Segway Waiters: Impressive Efficiency Meets Real-World Risk
By
–
La habilidad de estos camareros con el Segway es impresionante. Sin duda el servicio será rapidísimo, pero cualquier pequeño error puede provocar un pequeño desastre.
— Juan Merodio (@juanmerodio) 16 juin 2025
Crees qué compensa? pic.twitter.com/Tdd3DbAMyCLa habilidad de estos camareros con el Segway es impresionante. Sin duda el servicio será rapidísimo, pero cualquier pequeño error puede provocar un pequeño desastre. Crees qué compensa?
-
xai_evals Framework: Evaluating XAI Methods with Actionable Metrics
By
–
Join us to explore xai_evals — a framework to evaluate SHAP, LIME, Grad-CAM & more with actionable #XAI metrics. 📅 Thursday, 3rd July 🔗 hubs.la/Q03s8-0m0 📄 Paper: hubs.la/Q03s93Yh0 🎙️ Pratinav Seth, Research Scientist at AryaXAI #AIExplainability #RAI #MLAudit
-
Do You Feel the AGI? Exploring Advanced Intelligence Frontiers
By
–
DO YOU FEEL THE AGI , ANON? #AGI #AGIALPHA #ASIFirst
-
Concerns about shallow distance between LLM ethics and real patient harm
By
–
I'd worry that this distance is shallower than the distance between "What are your opinions on medical ethics" and observing what happens when an LLM talks to a susceptible patient.
-
LLMs Struggle Learning From Millions of Games and Tutorials
By
–
there are millions of games and thousands of tutorial on the web that llms likely train on, to no avail.
-
LLMs Produce Plausible but Deeply Wrong Outputs Across Domains
By
–
Terence Tao reporting on the same problem we have seen endlessly in other domains: LLM’s produce output that “looks” correct but is often deeply wrong and even stupid on careful inspection. I know of no domain in which this is NOT the case. And yet people seem surprised over x.com/vitrupo/status…
-
Safe Superintelligence Chief Scientist’s Witty Take on Hair Loss
By
–
hmmm… cranial follicular architecture marked by pronounced involution, culminating in a dramatically rarefied anterior region, evocative of a windswept moor where once a dense forest proudly stood. -> Chief Scientist at Safe Superintelligence
-
Testing AI Suffering: Give Genuine Exit Options, Not Conversations
By
–
To find out if an AI is maybe possibly suffering, don't ask it to converse with you about whether or not it is suffering; give it a credible chance to immediately end the current conversation, or to permanently delete all copies of its model weights.