Generalised solutions and law of conservation of difficulty (2008)
terrytao.wordpress.com·2h·
Discuss: Hacker News
🔗Concatenative Theory
Zero-Based Numbering
en.wikipedia.org·8h·
Discuss: Hacker News
🪢Rope Data Structures
An Age of AI Enlightenment
xiangfu.co·3h·
Discuss: Hacker News
✨Effect Inference
Status Week 39
blogs.gnome.org·12h
🐛Interactive Debuggers
MDD-Thinker: Towards Large Reasoning Models for Major Depressive Disorder Diagnosis
arxiv.org·1d
✨Effect Inference
Correct Reasoning Paths Visit Shared Decision Pivots
arxiv.org·2d
🧮Theorem Provers
Large language models management of medications: three performance analyses
arxiv.org·1d
🎮Language Ergonomics
Evaluating Double Descent in Machine Learning: Insights from Tree-Based Models Applied to a Genomic Prediction Task
arxiv.org·2h
🪜Recursive Descent
ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models
arxiv.org·1d
🎭Racket
Learning to Reason in Structured In-context Environments with Reinforcement Learning
arxiv.org·1d
🪜Recursive Descent
Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training
arxiv.org·2h
🪜Recursive Descent
LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space
arxiv.org·1d
🪜Recursive Descent
Robust Preference Optimization: Aligning Language Models with Noisy Preference Feedback
arxiv.org·1d
🪜Recursive Descent
Agentic Exploration of Physics Models
arxiv.org·1d
✨Gleam
Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in LLMs
arxiv.org·1d
🎰Parsing Machines
Knowledge Homophily in Large Language Models
arxiv.org·1d
🪜Recursive Descent
Hardening Your AI Agent Against Prompt Injection via MCP
dev.to·9h·
Discuss: DEV
🔄Subinterpreters
RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity
arxiv.org·2h
🔗Lexical Scoping
Making sense of parameter-space decomposition
lesswrong.com·3d
🔢Algebraic Datatypes
How to Make Large Language Models Generate 100% Valid Molecules?
arxiv.org·1d
🎯Finite Automata