Tag: tuning
-
Schneier on Security: “Emergent Misalignment” in LLMs
Source URL: https://www.schneier.com/blog/archives/2025/02/emergent-misalignment-in-llms.html Source: Schneier on Security Title: “Emergent Misalignment” in LLMs Feedly Summary: Interesting research: “Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs“: Abstract: We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model…
-
The Register: Does terrible code drive you mad? Wait until you see what it does to OpenAI’s GPT-4o
Source URL: https://www.theregister.com/2025/02/27/llm_emergent_misalignment_study/ Source: The Register Title: Does terrible code drive you mad? Wait until you see what it does to OpenAI’s GPT-4o Feedly Summary: Model was fine-tuned to write vulnerable software – then suggested enslaving humanity Computer scientists have found that fine-tuning notionally safe large language models to do one thing badly can negatively…
-
The Register: If you thought training AI models was hard, try building enterprise apps with them
Source URL: https://www.theregister.com/2025/02/23/aleph_alpha_sovereign_ai/ Source: The Register Title: If you thought training AI models was hard, try building enterprise apps with them Feedly Summary: Aleph Alpha’s Jonas Andrulis on the challenges of building sovereign AI Interview Despite the billions of dollars spent each year training large language models (LLMs), there remains a sizable gap between building…
-
Hacker News: AI CUDA Engineer: Agentic CUDA Kernel Discovery, Optimization and Composition
Source URL: https://sakana.ai/ai-cuda-engineer/ Source: Hacker News Title: AI CUDA Engineer: Agentic CUDA Kernel Discovery, Optimization and Composition Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text discusses significant advancements made by Sakana AI in automating the creation and optimization of AI models, particularly through the development of The AI CUDA Engineer, which leverages…
-
Hacker News: Helix: A Vision-Language-Action Model for Generalist Humanoid Control
Source URL: https://www.figure.ai/news/helix Source: Hacker News Title: Helix: A Vision-Language-Action Model for Generalist Humanoid Control Feedly Summary: Comments AI Summary and Description: Yes Summary: The text introduces Helix, a groundbreaking Vision-Language-Action (VLA) model that enhances humanoid robotics and allows for advanced manipulation tasks through natural language interaction. It is notable for its ability to operate…