Research Worth Reading Week 43/2025
pentesterlab.com·16h
🛡️Proof-Carrying Archives
Flag this post
NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge
arxiv.org·11h
💻Local LLMs
Flag this post
Building Better Software: Why Workflows Beat Code Every Time • Ben Smith & James Beswick • GOTO 2025
youtube.com·2h
🔄Reproducible Builds
Flag this post
Electronic Arts' AI Tools Are Creating More Work Than They Save
games.slashdot.org·1h
🏺Gaming Archaeology
Flag this post
PARL: Prompt-based Agents for Reinforcement Learning
arxiv.org·11h
🌳Context free grammars
Flag this post
I stopped looking for a single perfect AI coder and combined a web UI and CLI
⚔️Lean Tactics
Flag this post
Can Confidence Estimates Decide When Chain-of-thought is Necessary for Llms?
arxiv.org·11h
💻Local LLMs
Flag this post
Language Modeling with Hierarchical Reasoning Models: Lessons from 1M Parameters
📊Quantization
Flag this post
Automated Insight Amplification via Multi-Modal Graph Analytics and Reinforcement Learning
🤖AI Curation
Flag this post
Parsing Webpages with a LLM – Revisited
📝Concrete Syntax
Flag this post
From Questions to Queries: An AI-powered Multi-Agent Framework for Spatial Text-to-SQL
arxiv.org·11h
🔶Voronoi Diagrams
Flag this post
Code-enabled language models can outperform reasoning models on diverse tasks
arxiv.org·11h
🧠Intelligence Compression
Flag this post
JS/TS Functions Orchestrator
🔗Concatenative Programming
Flag this post
Additive Models Explained: A Computational Complexity Approach
arxiv.org·11h
🧮Kolmogorov Complexity
Flag this post
Automated Lagrangian Anomaly Detection via Real-Time Constraint Propagation
👁️System Observability
Flag this post
11 problems I have noticed building Agents (and fixes nobody talks about)
⚡Proof Automation
Flag this post
Instance-Adaptive Hypothesis Tests with Heterogeneous Agents
arxiv.org·11h
🔲Cellular Automata
Flag this post
Loading...Loading more...