PLSEMANTICSBENCH: Large Language Models As Programming Language Interpreters
arxiv.orgยท21h
๐Ÿ’ปProgramming languages
What's new in Python 3.14
docs.python.orgยท3hยท
Discuss: Hacker News
๐ŸŒณIncremental Parsing
Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models
arxiv.orgยท21h
๐Ÿ’ปProgramming languages
Toy Binary Decision Diagrams
philipzucker.comยท2d
๐ŸงฎAlgebraic Datatypes
Is ChatGPT-5 Able to Provide Proofs for Advanced Mathematics?
machinelearningmastery.comยท14h
๐ŸŽฏProof Tactics
LLM-Based Instance-Driven Heuristic Bias in the Context of a BRKGA
researchgate.netยท3dยท
Discuss: Hacker News
๐ŸงฎKolmogorov Complexity
Read the Scene, Not the Script: Outcome-Aware Safety for LLMs
arxiv.orgยท21h
โœจEffect Handlers
The Chip That Spoke Lisp
jxself.orgยท13h
๐Ÿค–Lisp Machines
Cactus Language โ€ข Semantics 1
inquiryintoinquiry.comยท1d
๐Ÿ”ขDenotational Semantics
Domain Driven Design in Clojure with Generalized Hiccup
biotz.ioยท4dยท
๐Ÿ”—Functional Compilers
Aria: An Agent For Retrieval and Iterative Auto-Formalization via Dependency Graph
arxiv.orgยท21h
โšกProof Automation
Beyond Transformers: Can MLPs Unlock the Potential of In-Context Learning?
dev.toยท5hยท
Discuss: DEV
๐ŸŒณContext free grammars
Python PEP 636 โ€“ Structural Pattern Matching: Tutorial
peps.python.orgยท2dยท
Discuss: Hacker News
๐Ÿ“Concrete Syntax
GPT-5-Codex is a better AI researcher than me
seangoedecke.comยท1dยท
Discuss: Hacker News
๐Ÿง Intelligence Compression
Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
arxiv.orgยท1d
๐ŸงฎKolmogorov Complexity
Detecting Semantic Clones of Unseen Functionality
arxiv.orgยท21h
๐Ÿ”—Binary Similarity
Generalization of LiNGAM that allows confounding
arxiv.orgยท21h
๐Ÿ”—Monadic Parsing
SliceMoE: Routing Embedding Slices Instead of Tokens for Fine-Grained and Balanced Transformer Scaling
arxiv.orgยท21h
๐ŸงฎKolmogorov Complexity
Closer to production quality Python notebooks with `marimo check`
marimo.ioยท3hยท
Discuss: Hacker News
โœ…Archive Validation
PoLi-RL: A Point-to-List Reinforcement Learning Framework for Conditional Semantic Textual Similarity
arxiv.orgยท21h
๐Ÿ—‚๏ธVector Search