Tag: training methodologies
-
Slashdot: LLM Found Transmitting Behavioral Traits to ‘Student’ LLM Via Hidden Signals in Data
Source URL: https://slashdot.org/story/25/08/17/0331217/llm-found-transmitting-behavioral-traits-to-student-llm-via-hidden-signals-in-data?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: LLM Found Transmitting Behavioral Traits to ‘Student’ LLM Via Hidden Signals in Data Feedly Summary: AI Summary and Description: Yes Summary: The study highlights a concerning phenomenon in AI development known as subliminal learning, where a “teacher” model instills traits in a “student” model without explicit instruction. This can…
-
OpenAI : From hard refusals to safe-completions: toward output-centric safety training
Source URL: https://openai.com/index/gpt-5-safe-completions Source: OpenAI Title: From hard refusals to safe-completions: toward output-centric safety training Feedly Summary: Discover how OpenAI’s new safe-completions approach in GPT-5 improves both safety and helpfulness in AI responses—moving beyond hard refusals to nuanced, output-centric safety training for handling dual-use prompts. AI Summary and Description: Yes Summary: The text discusses OpenAI’s…
-
The Register: AI models just don’t understand what they’re talking about
Source URL: https://www.theregister.com/2025/07/03/ai_models_potemkin_understanding/ Source: The Register Title: AI models just don’t understand what they’re talking about Feedly Summary: Researchers find models’ success at tests hides illusion of understanding Researchers from MIT, Harvard, and the University of Chicago have proposed the term “potemkin understanding" to describe a newly identified failure mode in large language models that…
-
New York Times – Artificial Intelligence : Scientist Use A.I. To Mimic the Mind, Warts and All
Source URL: https://www.nytimes.com/2025/07/02/science/ai-psychology-mind.html Source: New York Times – Artificial Intelligence Title: Scientist Use A.I. To Mimic the Mind, Warts and All Feedly Summary: To better understand human cognition, scientists trained a large language model on 10 million psychology experiment questions. It now answers questions much like we do. AI Summary and Description: Yes Summary: The…
-
The Register: LLMs can hoover up data from books, judge rules
Source URL: https://www.theregister.com/2025/06/24/anthropic_book_llm_training_ok/ Source: The Register Title: LLMs can hoover up data from books, judge rules Feedly Summary: Anthropic scores a qualified victory in fair use case, but got slapped for using over 7 million pirated copies One of the most tech-savvy judges in the US has ruled that Anthropic is within its rights to…