OpenSIR: Open-Ended Self-Improving Reasoner
arxiv.org·1d
🎨Computational Creativity
Flag this post
Thinking Like a Student: AI-Supported Reflective Planning in a Theory-Intensive Computer Science Course
arxiv.org·1h
🎨Computational Creativity
Flag this post
Regularization Through Reasoning: Systematic Improvements in Language Model Classification via Explanation-Enhanced Fine-Tuning
arxiv.org·1h
🔄Transformers
Flag this post
Between Myths and Metaphors: Rethinking LLMs for SRH in Conservative Contexts
arxiv.org·1h
💬Philosophy of Language
Flag this post
GDM: Consistency Training Helps Limit Sycophancy and Jailbreaks in Gemini 2.5 Flash
lesswrong.com·13h
✍️Writing Systems
Flag this post
Complex QA and language models hybrid architectures, Survey
arxiv.org·1d
📝NLP
Flag this post
Context7 is the most underrated MCP server you're not using for your local LLM
xda-developers.com·1d
📝NLP
Flag this post
Inferring multiple helper Dafny assertions with LLMs
arxiv.org·1d
🤖AI
Flag this post
Accumulating Context Changes the Beliefs of Language Models
arxiv.org·1d
🎲Bayesian Cognition
Flag this post
Can-t stop till you get enough
🤖AI
Flag this post
Loading...Loading more...