Retrieval Augmented Generation, Vector Search, Embeddings, Context

Nvidia Nemotron Is Now Available in Puter.js
developer.puter.com·1h·
Discuss: Hacker News
🤖Ai
Flag this post
Meta’s Generative Ads Model (GEM): The Central Brain Accelerating Ads Recommendation AI Innovation
engineering.fb.com·2d·
Discuss: Hacker News
💬Large Language Models
Flag this post
Researchers Surprised That With AI, Toxicity is Harder To Fake Than Intelligence
tech.slashdot.org·5h
🤖Ai
Flag this post
The emerging evidence on AI tutoring
tildes.net·17h·
Discuss: Substack
💬Large Language Models
Flag this post
3D artists are shunning AI generators, survey suggests
creativebloq.com·3h
💬Large Language Models
Flag this post
The top photos of the day by AP’s photojournalists - AP News
news.google.com·18h
📊Vector Databases
Flag this post
Show HN: AI Photo Cleaner iOS app (on-device processing)
news.ycombinator.com·2d·
Discuss: Hacker News
🤖Ai
Flag this post
Resource Allocation in Hybrid Radio-Optical IoT Networks using GNN with Multi-task Learning
arxiv.org·14h
💬Large Language Models
Flag this post
Baidu's latest ERNIE model brings visual reasoning to open-source AI
the-decoder.com·1h
🤖Ai
Flag this post
Robust Causal Discovery under Imperfect Structural Constraints
arxiv.org·1d
🤖Ai
Flag this post
Deep Pareto Reinforcement Learning for Multi-Objective Recommender Systems
arxiv.org·1d
🤖Ai
Flag this post
Optimizing Diversity and Quality through Base-Aligned Model Collaboration
arxiv.org·1d
💬Large Language Models
Flag this post
Quantifying Edits Decay in Fine-tuned LLMs
arxiv.org·1d
💬Large Language Models
Flag this post
Efficient Long-context Language Model Training by Core Attention Disaggregation
dev.to·8h·
Discuss: DEV
💬Large Language Models
Flag this post
A Practical Guide to Building AI Agents with Java and Spring AI - Part 2 - Add Memory
dev.to·1d·
Discuss: DEV
🤖Ai
Flag this post
Meta’s SPICE framework pushes AI toward self-learning without human supervision
infoworld.com·8h
💬Large Language Models
Flag this post
Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives
arxiv.org·1d
🤖Ai
Flag this post
Retracing the Past: LLMs Emit Training Data When They Get Lost
arxiv.org·1d
💬Large Language Models
Flag this post