Let’s talk about LLM guardrails
blog.adnansiddiqi.me·4h
🎯Proof Tactics
A very short, very blunt, book note
logicmatters.net·4d
⚔️Lean Theorem
Prime Portraits
archive.bridgesmathart.org·1d
📐Mathematical Art
Nicholas Renotte: I Spent 6 Weeks using Reinforcement Learning to Beat This GoDot Game
vibe.forem.com·4h·
Discuss: DEV
⚔️Lean Tactics
We May Have a Path to the Fundamental Theory of Physics (2020)
writings.stephenwolfram.com·8h·
Discuss: Hacker News
⏰Time Crystals
Sandy Maguire: Theorems for Free Redux
reasonablypolymorphic.com·2d·
Discuss: Hacker News
λLambda Encodings
94% of Developers Waste Tokens on Reasoning LLMs. Here's Why.
dev.to·1d·
Discuss: DEV
💻Local LLMs
In-Depth Analysis: "Attention Is All You Need"
dev.to·23h·
Discuss: DEV
🧠Intelligence Compression
2 Math Problems Fall to LLM: Tsumura's 554 solved, Majority Optimality Disproved
nednex.com·5d·
Discuss: Hacker News
🧮SMT Solvers
Unveiling the Power of Queues: A Journey into Data Structures and Algorithms
dev.to·2d·
Discuss: DEV
⚡Cache Theory
Data-Error Scaling Laws in Machine Learning on Combinatorial Mutation-prone Sets: Proteins and Small Molecules
arxiv.org·1d
🧮Kolmogorov Complexity
Where is Mathematics Going? Large Language Models and Lean Proof Assistant
hackaday.com·2d
⚙️Proof Engineering
Refactoring: A way to write better Code
dev.to·13h·
Discuss: DEV
⚙️Operational Semantics
Unraveling LCRE-Mediated Chromatin Loops: A Predictive Model for Gene Expression Fine-Tuning in Desert Genomes
dev.to·16h·
Discuss: DEV
📥Feed Aggregation
Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers
arxiv.org·1d
✓Automated Theorem Proving
Building Self-Correcting Database Agents with Meta's Llama-4-Scout: From Natural Language to SQL Insights
dev.to·1d·
Discuss: DEV
🗄️Database Internals
M\"obius transforms and Shapley values for vector-valued functions on weighted directed acyclic multigraphs
arxiv.org·3d
🕸️Graph Algorithms
Revisiting Mixout: An Overlooked Path to Robust Finetuning
arxiv.org·2d
🧠Learned Codecs
LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
arxiv.org·1d
🔲Cellular Automata
Expanding the Action Space of LLMs to Reason Beyond Language
arxiv.org·1d
💻Local LLMs