Intimate conversations with AI chatbots were visible to everyone
heise.deยท1d
๐Ÿ”“Hacking
Data Hoarder Uses AI to Create Searchable Database of Epstein Files
404media.coยท2d
๐ŸŒWARC Forensics
Strategic Pagination Patterns for APIs
roxeem.comยท23hยท
Discuss: Hacker News
๐Ÿ“Range Queries
Letโ€™s talk about LLM guardrails
blog.adnansiddiqi.meยท1dยท
Discuss: Hacker News
๐ŸŽฏProof Tactics
The Alien Artifact: DSPy and the Cargo Cult of LLM Optimization
data-monger.comยท19hยท
Discuss: Hacker News
๐Ÿ”Vector Forensics
An alternative to knowledge graphs for storing loosely structured content
fleetingswallow.comยท6dยท
Discuss: Hacker News
๐Ÿ•ธ๏ธKnowledge Graphs
Can an LLM Be a Black-Box Optimizer?
posgeo.wordpress.comยท1dยท
Discuss: Hacker News
๐ŸงฎKolmogorov Bounds
Microsoft only lets you opt out of AI photo scanning 3x a year
dev.toยท11hยท
Discuss: DEV
๐Ÿค–Archive Automation
Do We Really Need SFT? Prompt-as-Policy over Knowledge Graphs for Cold-start Next POI Recommendation
arxiv.orgยท2d
๐ŸŽฏContent Recommendation
How Google Translate & ChatGPT Work: The Transformer, Unboxed
dev.toยท2dยท
Discuss: DEV
๐Ÿง Learned Codecs
The 'Why' Algorithm: Building AI That Learns to Ask Questions
dev.toยท1dยท
Discuss: DEV
๐Ÿค–AI Curation
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
arxiv.orgยท2d
๐Ÿ“ผCassette Combinators
Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning
arxiv.orgยท2d
๐Ÿ“ŠLearned Metrics
GNN Predictions: Hidden Bugs and the Verification Nightmare by Arvind Sundararajan
dev.toยท1dยท
Discuss: DEV
โš™๏ธProof Engineering
ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving
arxiv.orgยท2d
๐ŸŒ€Riemannian Computing
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.toยท1dยท
Discuss: DEV
๐Ÿ“ŠMulti-vector RAG
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
arxiv.orgยท4d
๐ŸงฎKolmogorov Complexity
Stress-Testing Model Specs Reveals Character Differences among Language Models
arxiv.orgยท2d
๐Ÿ“‹Document Grammar
On the Relationship Between the Choice of Representation and In-Context Learning
arxiv.orgยท2d
๐Ÿ“ŠLearned Metrics