Variation Is King, Not the Average
xmrit.com·1d·
Discuss: Hacker News
🔄Reproducible Builds
Flag this post
Mathematics solves problems by pen and paper. CS helps us to go far beyond that
cacm.acm.org·1d·
Discuss: Hacker News
🧠Automated Reasoning
Flag this post
Finding Signal Through the Noise
elijahpotter.dev·1d·
Discuss: Hacker News
👁️System Observability
Flag this post
A Thesis and Playbook for Edge AI
ondeviceguy.substack.com·1d·
Discuss: Substack
🖥️Self-hosted Infrastructure
Flag this post
The Next Big Thing
semiengineering.com·1d·
Discuss: Hacker News
👁️System Observability
Flag this post
Sorting by Strip Swaps is NP-Hard
arxiv.org·9h
⏱️Computational Complexity
Flag this post
⚠️ Most Developers Are Using AI Wrong — Here’s How to Fix It
dev.to·17h·
Discuss: DEV
🔄Reproducible Builds
Flag this post
STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack
arxiv.org·9h
🧩Parser Combinators
Flag this post
Python Integration for Scryer Prolog Using FFI (Research Project)
github.com·20h·
Discuss: Hacker News
📦Module Systems
Flag this post
Why Most Manufacturers Still Trust 1980s Quality Control (and How AI Is Quietly Fixing It)
dev.to·4h·
Discuss: DEV
👁️System Observability
Flag this post
Weak-To-Strong Generalization
lesswrong.com·2d
🔤Kleene Algebra
Flag this post
Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals
arxiv.org·1d
📐Linear Algebra
Flag this post
This is one way I use AI for coding
dev.to·23h·
Discuss: DEV
🧮Z3 Solver
Flag this post
Benchmarking Generative AI Against Bayesian Optimization for Constrained Multi-Objective Inverse Design
arxiv.org·9h
🧮SMT Solvers
Flag this post
Scaling Coding-Agent RL to 32x H100s. 160% Improvement on Stanford's TBench
github.com·1d·
🌐ActivityPub
Flag this post
The Hardest Problem in AI: Human Context
dev.to·7h·
Discuss: DEV
🧠Automated Reasoning
Flag this post
Feature-Guided Analysis of Neural Networks: A Replication Study
arxiv.org·9h
🧠Automated Reasoning
Flag this post