Research Worth Reading Week 43/2025
pentesterlab.com·13h
🛡️Proof-Carrying Archives
Flag this post
Show HN: RightMindMath and Arithmetic Fluency
rightmindmath.com·21h·
Discuss: Hacker News
🧮SMT Solvers
Flag this post
How to Scale LLM Apps Without Exploding Your Cloud Bill
hackernoon.com·14h
📄Text Chunking
Flag this post
Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP
arxiv.org·7h
🧮SMT Solvers
Flag this post
LLMs Are Bottlenecked by Linear Interfaces
handmadeoasis.com·12h·
Discuss: Hacker News
📏Linear Logic
Flag this post
Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
arxiv.org·7h
🎵Audio ML
Flag this post
Formal or not formal? That is the question in AI for theorem proving.
xenaproject.wordpress.com·4d·
🔬Lean
Flag this post
String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation
arxiv.org·7h
🧪Binary Fuzzing
Flag this post
We Programmers Need "Results"
rockyj-blogs.web.app·2d·
Discuss: Hacker News
📜Proof Carrying Code
Flag this post
AI Discovers Novel Cancer Drug, or Did It?
mindprison.cc·8h·
Discuss: Hacker News
🔲Cellular Automata
Flag this post
InnoGate: Anti-Piracy Research Discovery Platform with AI-Powered RAG and Auth0 FGA
dev.to·4h·
Discuss: DEV
🔌Archive APIs
Flag this post
The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning
arxiv.org·7h
🌐NetworkProtocols
Flag this post
Agentic AI from First Principles: Reflection
towardsdatascience.com·2d
Effect Handlers
Flag this post
Understanding Type-Based Alias Analysis in C and C++
kdab.com·11m·
Discuss: Hacker News
🔒Type Safety
Flag this post
PARL: Prompt-based Agents for Reinforcement Learning
arxiv.org·7h
🌳Context free grammars
Flag this post
I stopped looking for a single perfect AI coder and combined a web UI and CLI
xor01.substack.com·19h·
Discuss: DEV, Substack
⚔️Lean Tactics
Flag this post
Corecursion
en.wikipedia.org·2d·
Discuss: Hacker News
λLambda Encodings
Flag this post
Can Confidence Estimates Decide When Chain-of-thought is Necessary for Llms?
arxiv.org·7h
💻Local LLMs
Flag this post
Parsing Webpages with a LLM – Revisited
hdembinski.github.io·2d·
Discuss: Hacker News
📝Concrete Syntax
Flag this post