Generalised solutions and law of conservation of difficulty (2008)
terrytao.wordpress.comยท8hยท
Discuss: Hacker News
๐Ÿ”—Concatenative Theory
Status Week 39
blogs.gnome.orgยท18h
๐Ÿ›Interactive Debuggers
An Age of AI Enlightenment
xiangfu.coยท10hยท
Discuss: Hacker News
โœจEffect Inference
Automated Adaptive T-Cell Receptor Sequencing Optimization via Bayesian Hyperparameter Tuning
dev.toยท1hยท
Discuss: DEV
๐Ÿ“‹JSON Parsing
Learning to Reason in Structured In-context Environments with Reinforcement Learning
arxiv.orgยท1d
๐ŸชœRecursive Descent
ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models
arxiv.orgยท1d
๐ŸŽญRacket
Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training
arxiv.orgยท8h
๐ŸชœRecursive Descent
LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space
arxiv.orgยท1d
๐ŸชœRecursive Descent
Robust Preference Optimization: Aligning Language Models with Noisy Preference Feedback
arxiv.orgยท1d
๐ŸชœRecursive Descent
Agentic Exploration of Physics Models
arxiv.orgยท1d
โœจGleam
Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in LLMs
arxiv.orgยท1d
๐ŸŽฐParsing Machines
Knowledge Homophily in Large Language Models
arxiv.orgยท1d
๐ŸชœRecursive Descent
RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity
arxiv.orgยท8h
๐Ÿ”—Lexical Scoping
How to Make Large Language Models Generate 100% Valid Molecules?
arxiv.orgยท1d
๐ŸŽฏFinite Automata
MARCOS: Deep Thinking by Markov Chain of Continuous Thoughts
arxiv.orgยท1d
๐ŸชœRecursive Descent
From Monolith to Monorepo: Building Faster with Turborepo, pnpm and Capacitor
dev.toยท1dยท
Discuss: DEV
๐Ÿ“ฆMonorepos
Making sense of parameter-space decomposition
lesswrong.comยท3dยท
Discuss: Hacker News
๐Ÿ”ขAlgebraic Datatypes