RegEx Crossword
jimbly.github.io·1d·
Discuss: Hacker News
🔤Morris-Pratt
Flag this post
The End of Shouting: Prompts as Programs in GPT-5
robert-glaser.de·3d·
Discuss: Lobsters, Hacker News
✓Automated Theorem Proving
Flag this post
We Programmers Need "Results"
rockyj-blogs.web.app·4d·
Discuss: Hacker News
📜Proof Carrying Code
Flag this post
Vectorizing for Fun and Performance
ibm.com·9h·
Discuss: Hacker News
⚡SIMD Vectorization
Flag this post
TypeAgent: Microsoft's Open Source Personal Agent Architecture
github.com·2d·
Discuss: Hacker News
⚡Proof Automation
Flag this post
Uncovering the Potential Risks in Unlearning: Danger of English-only Unlearning in Multilingual LLMs
arxiv.org·22h
💻Local LLMs
Flag this post
GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks
arxiv.org·1d
🕸️Graph Embeddings
Flag this post
Show HN: E2E Testing for Chatbots
github.com·9h·
Discuss: Hacker News
🔍Concolic Testing
Flag this post
Politically Speaking: LLMs on Changing International Affairs
arxiv.org·22h
✅Formal Methods
Flag this post
The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning
arxiv.org·2d
🌐NetworkProtocols
Flag this post
Wacl – A Tcl Distribution for WebAssembly
github.com·22h·
Discuss: Hacker News
🕸️WebAssembly
Flag this post
Linear Audio Dreams: Injecting Sanity into Autoencoder Latent Spaces by Arvind Sundararajan
dev.to·1d·
Discuss: DEV
🎧Learned Audio
Flag this post
WebAssembly 3.0 and the Infrastructure We Actually Need
dev.to·20h·
Discuss: DEV
🌐WASI
Flag this post
PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading
arxiv.org·1d
🔍Information Retrieval
Flag this post
OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning
arxiv.org·22h
🔍Information Retrieval
Flag this post
Debugging AI in Production: Root Cause Analysis with Observability
dev.to·5h·
Discuss: DEV
👁️System Observability
Flag this post
Why the Model Context Protocol is the Future of AI Integration
dev.to·5h·
Discuss: DEV
🔌Interface Evolution
Flag this post
OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models
arxiv.org·1d
🧠Machine Learning
Flag this post
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
arxiv.org·1d
💻Local LLMs
Flag this post
OpenFold3-Preview
github.com·1d·
Discuss: Hacker News
🔓Open Source Software
Flag this post