Doing Math with Embeddings for Better AI Ad Targeting
ethicalads.ioยท11hยท
Discuss: Hacker News
๐ŸงฎVector Embeddings
Build a Perfect Blog with FastAPI: Visitor Analytics
dev.toยท22hยท
Discuss: DEV
โš–๏ธFeed Ranking
Scalable In-context Ranking with Generative Models
arxiv.orgยท1d
โš–๏ธFeed Ranking
Unlocking Faster Insights with Experimenter-Defined Segmentations
etsy.comยท19h
๐Ÿ“Document Chunking
Changes in ipSpace.net RSS Feeds
blog.ipspace.netยท1d
๐Ÿ“กRSS
SigmaEval โ€“ statistical evaluation for GenAI apps
github.comยท22hยท
Discuss: Hacker News
๐Ÿ”Concolic Testing
Know Your Customer or Fail: A Senior-Level, AI-Powered Market Research Playbook
dev.toยท15hยท
Discuss: DEV
๐ŸŽฏContent Recommendation
What RSS is and why we should keep using it (2022)
harisont.github.ioยท18hยท
Discuss: Hacker News
๐Ÿ“ฐRSS Reading Practices
Algorithmic Archive Project: Use Cases (1/3)
blogs.bodleian.ox.ac.ukยท2d
๐Ÿ“ŠCitation Graphs
LLM Optimization Notes: Memory, Compute and Inference Techniques
gaurigupta19.github.ioยท2dยท
Discuss: Hacker News
๐Ÿ’ปLocal LLMs
Automated Content Marketing at Spotify
engineering.atspotify.comยท3dยท
Discuss: Hacker News
๐Ÿ”ƒFeed Algorithms
Building on vibes: Lessons from three years with LLMs
world.hey.comยท2hยท
Discuss: Hacker News
๐ŸŒ€Brotli Internals
I Built a Prompt to Optimize My Blog for Both Google and AI Overviews
dev.toยท2dยท
Discuss: DEV
๐ŸŒ€Brotli Internals
Show HN: PlayAiOdds โ€“ Football probabilities from AI and mathematical models
playaiodds.comยท6hยท
Discuss: Hacker News
๐Ÿง Machine Learning
Own your AI: Learn how to fine-tune Gemma 3 270M and run it on-device
developers.googleblog.comยท12h
๐Ÿ’ปLocal LLMs
Enhancing Synthetic Data Generation via Adaptive Kernel Density Estimation with Bayesian Optimization
dev.toยท4hยท
Discuss: DEV
๐Ÿง Machine Learning
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
huggingface.coยท3hยท
Discuss: Hacker News
๐Ÿ“ŠLearned Metrics
Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences
arxiv.orgยท1d
๐Ÿง Intelligence Compression
Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
arxiv.orgยท7h
๐Ÿ’ปLocal LLMs
Access Control Policy Generation from High-Level Natural Language Requirements
dl.acm.orgยท14hยท
Discuss: Hacker News
๐Ÿ”’Language-based security