Evaluating the Sensitivity of LLMs to Harmful Contents in Long Input
arxiv.orgยท9h
๐ŸŒ€Brotli Internals
GaloisInc/parameterized-utils
github.comยท12h
๐ŸงฎAlgebraic Datatypes
Cactus Language โ€ข Semantics 2
inquiryintoinquiry.comยท26m
๐Ÿ”ขDenotational Semantics
JSON Schema Compatibility and the Robustness Principle
yokota.blogยท21hยท
Discuss: Hacker News
๐Ÿ“‹Protocol Buffers
Reviving Lost Tongues: AI-Powered Grammar for Language Preservation
dev.toยท13hยท
Discuss: DEV
๐ŸŒณContext free grammars
The Dwarves Beneath the Kernel: Forging BTF for eBPF
bootlin.comยท1h
๐Ÿ“บVT100
What's new in Python 3.14
docs.python.orgยท15hยท
๐ŸŒณIncremental Parsing
SigmaEval โ€“ statistical evaluation for GenAI apps
github.comยท1hยท
Discuss: Hacker News
๐Ÿ”Concolic Testing
Three Solutions to Nondeterminism in AI
blog.hellas.aiยท1hยท
Discuss: Hacker News
๐ŸŽฏPerformance Proofs
Taming Video Processing Chaos with Domain-Driven Design in Symfony
hackernoon.comยท9h
๐ŸŒŠStreaming Systems
Static Bundle Object: Modernizing Static Linking
medium.comยท22hยท
Discuss: Hacker News
๐Ÿ”—Static Linking
Toy Binary Decision Diagrams
philipzucker.comยท2d
๐ŸงฎAlgebraic Datatypes
Structured Cognition for Behavioral Intelligence in Large Language Model Agents: Preliminary Study
arxiv.orgยท9h
๐Ÿง Intelligence Compression
Latency vs. Accuracy for LLM Apps โ€” How to Choose and How a Memory Layer Lets You Win Both
dev.toยท1dยท
Discuss: DEV
โšกPerformance Mythology
Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models
arxiv.orgยท1d
๐Ÿ”—Parser Combinators
Test Case Generation from Bug Reports via Large Language Models: A Cognitive Layered Evaluation Framework
arxiv.orgยท9h
๐Ÿ”Concolic Testing
Python PEP 636 โ€“ Structural Pattern Matching: Tutorial
peps.python.orgยท3dยท
Discuss: Hacker News
๐Ÿ“Concrete Syntax
Detecting Distillation Data from Reasoning Models
arxiv.orgยท1d
โš™๏ธABNF Mining
Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offs
arxiv.orgยท1d
โš™๏ธTLA+
Evaluating LLM Safety Across Child Development Stages: A Simulated Agent Approach
arxiv.orgยท9h
๐Ÿ’ปProgramming languages