It’s wild… though between this and cloud seeding, how do we make sure we don’t mess it up?
SAFETY
-
AI Alarmism Losing Credibility Over Time
By
–
AI alarmism loses credibility with every day that passes. The contrast with the AI panic of a year ago is striking.
-
US Government Takes Action Against Harmful AI Applications
By
–
I’m encouraged at the progress of the U.S. government at moving to stem harmful AI applications. Two examples are the new Federal Trade Commission (FTC) ban on fake product reviews and the DEFIANCE Act, which imposes punishments for creating and disseminating non-consensual
-
Opinion: RLHF vs the ‘Base Model’ Myth
By
–
People hear RLHF and think censorship, so they expect the base model to be untainted, honest, free — all those nice Grokian promises. And it is! But it’s also helplessly insane, and lost in the delusion the entire world is improv theater. “Base model” — not “based model.”
-
Safety and privacy are baked into fine-tuned models.
By
–
But it’s not just about power—safety and privacy are baked in. Fine-tuned models don’t share data with other models, and OpenAI has layered on extra safety measures to ensure ethical use.
-
Physical AI Robots Deployed in Real-World Factory and Warehouse Settings
By
–
Physical AI is here. At Robust AI we have developed the foundations for physical robots that do real work in real installations, and we have deployed them in both factories and warehouses. One key is to make them aware of humans so that they play nice, another is zero integration
-
Gemini Becomes Unresponsive With Three Korean Characters
By
–
You can cause Gemini to become unresponsive by simply entering the three characters “자인이” @OfficialLoganK
-
Grok-2 Pushes AI Ethics And Innovation Boundaries
By
–
AI Gone Wild: How Grok-2 Is Pushing The Boundaries Of Ethics And Innovation Elon Musk's latest #AI model is breaking barriers and raising eyebrows. This article explores how #Grok-2 is challenging our understanding of AI #capabilities and #ethics and what it means for the
-
Cybench: Framework for Evaluating Language Models Cybersecurity Capabilities
By
–
Cybench A Framework for Evaluating Cybersecurity Capabilities and Risk of Language Models discuss: https://
huggingface.co/papers/2408.08
926
… Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have the potential to