Hacker News
- Manipulating Chess-GPT's World Model https://adamkarvonen.github.io/machine_learning/2024/03/20/chess-gpt-interventions.html 36 comments
Linking pages
Linked pages
- GPT-3, Bloviator: OpenAI’s language generator has no idea what it’s talking about | MIT Technology Review https://www.technologyreview.com/2020/08/22/1007539/gpt3-openai-language-generator-artificial-intelligence-ai-opinion/ 303 comments
- Giving GPT-3 a Turing Test https://lacker.io/ai/2020/07/06/giving-gpt-3-a-turing-test.html 278 comments
- [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task https://arxiv.org/abs/2210.13382 148 comments
- Chess-GPT’s Internal World Model | Adam Karvonen https://adamkarvonen.github.io/machine_learning/2024/01/03/chess-world-models.html 112 comments
- A Mathematical Framework for Transformer Circuits https://transformer-circuits.pub/2021/framework/index.html 9 comments
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learning https://transformer-circuits.pub/2023/monosemantic-features/index.html 5 comments
- GitHub - adamkarvonen/chess_llm_interpretability: Evaluating an LLM trained on chess PGN strings using techniques from the Othello World Models paper. https://github.com/adamkarvonen/chess_llm_interpretability 2 comments
- [2310.01405] Representation Engineering: A Top-Down Approach to AI Transparency https://arxiv.org/abs/2310.01405 0 comments
Related searches:
Search whole site: site:adamkarvonen.github.io
Search title: Manipulating Chess-GPT’s World Model | Adam Karvonen
See how to search.