Let’s talk about LLM guardrails
blog.adnansiddiqi.me·57m
🎯Proof Tactics
GaloisInc/parameterized-utils
github.com·3d
🧮Algebraic Datatypes
Slip – A Lisp System in JavaScript
lisperator.net·21h·
Discuss: Hacker News
🔗Lisp
Effective and Stealthy One-Shot Jailbreaks on Deployed Mobile Vision-Language Agents
arxiv.org·1d
🕵️Vector Smuggling
The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models
arxiv.org·1d
🤖Grammar Induction
METRICALARGS: A Taxonomy for Studying Metrical Poetry with LLMs
arxiv.org·1d
📊HyperLogLog
On knot detection via picture recognition
arxiv.org·2d
🕸️Algebraic Topology
Nearest Neighbor CCP-Based Molecular Sequence Analysis
arxiv.org·1d
🔄Burrows-Wheeler
A Manifesto for the Programming Desperado
github.com·19h·
Discuss: Hacker News
💻Programming languages
Evaluating Small Vision-Language Models on Distance-Dependent Traffic Perception
arxiv.org·1d
🧠Machine Learning
Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
arxiv.org·1d
🧮Theorem Proving
Markdown2pdf – pure md to pdf transpiler implementation in Rust
github.com·1d·
Discuss: Hacker News
📄PDF Internals
Beyond Vector Search: Building a RAG That *Actually* Understands Your Data
dev.to·1d·
Discuss: DEV
🗂️Vector Databases
Evaluating OCR performance on food packaging labels in South Africa
arxiv.org·4d
📄OCR
ParsTranslit: Truly Versatile Tajik-Farsi Transliteration
arxiv.org·1d
📜Digital Philology
StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering
arxiv.org·2d
🧠Intelligence Compression
Show HN: I built a LSP with its own parser to learn Rust
github.com·7h·
Discuss: Hacker News
⚡Dependent Rust
A Proof of the Riemann Hypothesis
dev.to·2d·
Discuss: DEV
⚔️Lean Theorem
Two-Stage Voting for Robust and Efficient Suicide Risk Detection on Social Media
arxiv.org·1d
💾Binary Linguistics
LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
arxiv.org·1d
🔗Parser Combinators