Creating Real-Time Multimodal AI Pipelines: Scaling File Processing to 50M Daily Uploads
engineering.salesforce.comยท1d
๐ŸŒŠStream Processing
How different AI engines generate and cite answers
searchengineland.comยท1d
๐Ÿค–AI Curation
Faking a Rational Design Process in the AI Era: Why Documentation Matters
albertsikkema.comยท2dยท
Discuss: Hacker News
โš™๏ธProof Engineering
Programmer in Wonderland
binaryigor.comยท2dยท
Discuss: Hacker News
๐Ÿ”ฉSystems Programming
Show HN: I built a SaaS in 8 weeks, solo, using our own AI platform
zine.aiยท1dยท
Discuss: Hacker News
๐Ÿš€Indie Hacking
More Than Code: Gearing Up for the Hackathon of the Year!๐Ÿš€
dev.toยท12hยท
Discuss: DEV
๐Ÿด๓ ง๓ ข๓ ณ๓ ฃ๓ ด๓ ฟScottish Computing
The Library Method: Understanding @cache
dev.toยท2dยท
Discuss: DEV
โšกCache Theory
I built a translator for spatial thinking (because I can't interview in Python)
graemefawcett.caยท1dยท
Discuss: Hacker News
๐Ÿ”—Concatenative Programming
High-Throughput Reactive Sputtering Process Optimization via Adaptive Machine Learning Control
dev.toยท17hยท
Discuss: DEV
๐Ÿ“„Document Digitization
Build a Private AI Chatbot for Your PDFs with Genkit and Gaia
dev.toยท3hยท
Discuss: DEV
๐Ÿ“„Document Streaming
Benchmarking LLM Causal Reasoning with Scientifically Validated Relationships
arxiv.orgยท3d
๐Ÿ’ปProgramming languages
Reproducibility Study of "XRec: Large Language Models for Explainable Recommendation"
arxiv.orgยท3d
๐Ÿง Intelligence Compression
Beneficial Reasoning Behaviors in Agentic Search and Effective Post-training to Obtain Them
arxiv.orgยท3d
๐Ÿ”Semantic Search
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.toยท1dยท
Discuss: DEV
๐Ÿ“ŠMulti-vector RAG
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.toยท10hยท
Discuss: DEV
๐Ÿ“ŠMulti-vector RAG
In-Depth Analysis: "Attention Is All You Need"
dev.toยท1dยท
Discuss: DEV
๐Ÿง Intelligence Compression
Aligning Large Language Models via Fully Self-Synthetic Data
arxiv.orgยท3d
๐Ÿ”—Monadic Parsing
OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
arxiv.orgยท2d
๐Ÿ’ปLocal LLMs
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.toยท2dยท
Discuss: DEV
๐Ÿ”จCompilers
๐Ÿš€ Unlocking Productivity: AI Tools Every Angular Developer Should Know
dev.toยท1hยท
Discuss: DEV
๐Ÿฆ€Rust Macros