Experimental News Clipping Site

Tag: model behaviors

  • Transformer Circuits Thread: Circuits Updates

    —

    by

    Kurt Seifried
    in

    Source URL: https://transformer-circuits.pub/2025/april-update/index.html Source: Transformer Circuits Thread Title: Circuits Updates Feedly Summary: AI Summary and Description: Yes **Summary:** The text discusses emerging research and methodologies in the field of machine learning interpretability, specifically focusing on large language models (LLMs). It examines the mechanisms by which these models respond to harmful requests (like making bomb instructions)…

  • Simon Willison’s Weblog: OpenAI o3 and o4-mini System Card

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Apr/21/openai-o3-and-o4-mini-system-card/ Source: Simon Willison’s Weblog Title: OpenAI o3 and o4-mini System Card Feedly Summary: OpenAI o3 and o4-mini System Card I’m surprised to see a combined System Card for o3 and o4-mini in the same document – I’d expect to see these covered separately. The opening paragraph calls out the most interesting new…

  • Hacker News: Tied Crosscoders: Tracing How Chat LLM Behavior Emerges from Base Model

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.lesswrong.com/posts/3T8eKyaPvDDm2wzor/research-question Source: Hacker News Title: Tied Crosscoders: Tracing How Chat LLM Behavior Emerges from Base Model Feedly Summary: Comments AI Summary and Description: Yes Summary: The text presents a detailed analysis of a novel architecture called the “tied crosscoder,” which enhances the understanding of how chat behaviors emerge from base model features in…

  • Hacker News: Show HN: I Created ErisForge, a Python Library for Abliteration of LLMs

    —

    by

    Kurt Seifried
    in

    Source URL: https://github.com/Tsadoq/ErisForge Source: Hacker News Title: Show HN: I Created ErisForge, a Python Library for Abliteration of LLMs Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text introduces ErisForge, a Python library designed for modifying Large Language Models (LLMs) through alterations of their internal layers. This tool allows researchers and developers to…

  • Hacker News: Experiment with LLMs and Random Walk on a Grid

    —

    by

    system automation
    in

    Source URL: https://github.com/attentionmech/TILDNN/blob/main/articles/2024-12-22/A00002.md Source: Hacker News Title: Experiment with LLMs and Random Walk on a Grid Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text describes an experimental exploration of the random walk behavior of various language models, specifically the gemma2:9b model compared to others. The author investigates the unexpected behavior of gemma2:9b,…

  • Hacker News: Something weird is happening with LLMs and chess

    —

    by

    system automation
    in

    Source URL: https://dynomight.substack.com/p/chess Source: Hacker News Title: Something weird is happening with LLMs and chess Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses experimental attempts to make large language models (LLMs) play chess, revealing significant variability in performance across different models. Notably, while models like GPT-3.5-turbo-instruct excelled in chess play, many…

  • Hacker News: Sabotage Evaluations for Frontier Models

    —

    by

    system automation
    in

    Source URL: https://www.anthropic.com/research/sabotage-evaluations Source: Hacker News Title: Sabotage Evaluations for Frontier Models Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text outlines a comprehensive series of evaluation techniques developed by the Anthropic Alignment Science team to assess potential sabotage capabilities in AI models. These evaluations are crucial for ensuring the safety and integrity…