Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification
arxiv.org·6h
🧮Kolmogorov Complexity
Types That Count: Journey across Qualitative and Quantitative Intersection Types
iris.unito.it·2d·
Discuss: Hacker News
🔍Type Inference
2025-07-16: Understanding Hallucination in Large Language Models: Challenges and Opportunities
ws-dl.blogspot.com·10h·
Discuss: ws-dl.blogspot.com
✨Effect Handlers
Rethinking Distributed Computing for the AI Era
cacm.acm.org·15h
⚡Incremental Computation
SmartDocs AI - Intelligent Documentation Search with Algolia MCP Server
dev.to·19h·
Discuss: DEV
🌀Brotli Internals
Cactus Language • Stylistics 4
inquiryintoinquiry.com·1d
🌳Context free grammars
Effectively Zero-Knowledge Proofs for NP with No Interaction, No Setup
eccc.weizmann.ac.il·1d·
Discuss: Hacker News
🎯Interactive Provers
AwesomeAssertions/AwesomeAssertions
github.com·20h
✅Format Verification
Functional Abstract Interpretation
simon.peytonjones.org·2d·
Discuss: Hacker News
🔗Functional Compilers
Boffins detail new algorithms to losslessly boost AI perf by up to 2.8x
theregister.com·47m
💻Local LLMs
Pointwise definable end-extensions of models of arithmetic and set theory, Changchun, China, July 2025
jdh.hamkins.org·2d
🏗️Constructive Mathematics
CRABS: A syntactic-semantic pincer strategy for bounding LLM interpretation of Python notebooks
arxiv.org·6h
💻Programming languages
I've been coding with AI for two years. Here is what I've learned
nathanpeck.com·8h·
Discuss: Hacker News
💾Persistence Strategies
This “smart coach” helps LLMs switch between text and code
news.mit.edu·6h
💻Local LLMs
Students, here are 5 key things to know when learning how to train large language models
techradar.com·1d
💻Local LLMs
A Wide Reduction Trick (2022)
words.filippo.io·7h·
Discuss: Lobsters, Hacker News
🌳Archive Merkle Trees
Heterogeneous Dynamic Logic: Provability Modulo Program Theories
arxiv.org·3d
🧠Computational Logic
An LLM Router That Thinks Like an Engineer
medium.com·1d·
Discuss: Hacker News
📡BGP Archaeology
Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning
arxiv.org·1d
🌳Context free grammars
Zig Interface Revisited
williamw520.github.io·17h·
Discuss: Hacker News
🧩WASM Components