Nonmonotonic Logic
cambridge.org·17h·
Discuss: Hacker News
🔬Logic in Computer Science
Flag this post
The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
arxiv.org·6h
Effect Handlers
Flag this post
Infrastructure Should Be Inferred, Not Written (and LLMs Are Why)
ivan.codes·15h·
Discuss: Hacker News
🔒WASM Capabilities
Flag this post
Signature schemes you've never heard about – Kobi Gurkan
kobi.leaflet.pub·1h·
Discuss: Hacker News
🌳Archive Merkle Trees
Flag this post
LLMs Are Bottlenecked by Linear Interfaces
handmadeoasis.com·1d·
Discuss: Hacker News
💻Local LLMs
Flag this post
Mapping Faithful Reasoning in Language Models
arxiv.org·6h
🎯Dependent Parsing
Flag this post
Reasoning Models Reason Well, Until They Don't
arxiv.org·6h
🧮Constraint SMT
Flag this post
My First Rust Project
binwang.me·6h
🦀Rust Macros
Flag this post
Craft and quality beat speed and scale, with or without agents
stackoverflow.blog·2h
🔒WASM Capabilities
Flag this post
Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces
arxiv.org·6h
Automated Theorem Proving
Flag this post
AgentKit: How Efficient Laziness Fixes Fragile LLM Workflows
dev.to·1d·
Discuss: DEV
⚙️Proof Engineering
Flag this post
An intro to the Tensor Economics blog
splittinginfinity.substack.com·14h·
Discuss: Substack
💻Local LLMs
Flag this post
Understanding Type-Based Alias Analysis in C and C++
kdab.com·22h·
Discuss: Hacker News
🔒Type Safety
Flag this post
Grounding LLMs with Symbolic Planning
theelderscripts.com·17h·
Discuss: Hacker News
⚔️Lean Tactics
Flag this post
Interpreting and Mitigating Unwanted Uncertainty in LLMs
arxiv.org·6h
💻Local LLMs
Flag this post
CLIN-LLM: A Safety-Constrained Hybrid Framework for Clinical Diagnosis and Treatment Generation
arxiv.org·6h
🧠Machine Learning
Flag this post
Think Twice: Branch-and-Rethink Reasoning Reward Model
arxiv.org·6h
Incremental Computation
Flag this post
Turing Machine Visualization (2016)
turingmachine.io·12h·
Discuss: Hacker News
🎞️Tape Combinatorics
Flag this post
LightAgent: Mobile Agentic Foundation Models
arxiv.org·6h
⚙️TLA+
Flag this post