Show HN: Virtual Ontologies with Claude Code
medium.com·1d·
Discuss: Hacker News
🧩Design Systems
Remembrance Agent A continuously running automated information retrieval system
bradleyrhodes.com·1d·
Discuss: Hacker News
🔍User Research
With just a few messages, biased AI chatbots swayed people's political views
phys.org·15h
🧩Psychology
Fine-tuning with GPT-OSS and Hugging Face Transformers
cookbook.openai.com·1d·
Discuss: Hacker News
🤖AI
How to Use NLP to Extract Business Insights from Chat Data
dev.to·4d·
Discuss: DEV
🔍User Research
How LLMs See the World
blog.bytebytego.com·2d
🤖AI
We beat GPT-4o's baseline with a simple re-prompting loop
aimon.ai·1d·
Discuss: Hacker News
🤖AI
Quantum-RAG and PunGPT2: Advancing Low-Resource Language Generation and Retrieval for the Punjabi Language
arxiv.org·2d
🔷TypeScript
How Deep Is Representational Bias in LLMs? The Cases of Caste and Religion
arxiv.org·4h
🧩Psychology
Show HN: Using DSPy to enrich a dataset of the Nobel laureate network
blog.kuzudb.com·2d·
Discuss: Hacker News
🤖AI
Graph Representation Learning with Massive Unlabeled Data for Rumor Detection
arxiv.org·4h
🧩Psychology
Outrank the Algorithm: What LLMs Look for When They ‘Choose’ Your Content
hackernoon.com·1d
🧩Psychology
Your 2025 Roadmap to Becoming an AI Engineer for Free for Vue.js Developers
dev.to·15h·
Discuss: DEV
🤖AI
ProKG-Dial: Progressive Multi-Turn Dialogue Construction with Domain Knowledge Graphs
arxiv.org·2d
🔍User Research
TalkDep: Clinically Grounded LLM Personas for Conversation-Centric Depression Screening
arxiv.org·4h
🔍User Research
Key-Augmented Neural Triggers for Knowledge Sharing
arxiv.org·1d
🧩Design Systems
Proof of how fast AI is developing: on the left a clip of Google Deepmind's Genie 2 from December 2024, on the right a clip of Genie 3 from August 2025.
threadreaderapp.com·1d
🤖AI
A new study found that LLMs like ChatGPT fell for fake clinical details 50–82% of the time. Even the best prompts could not stop all hallucinations
nature.com·19h
🧩Psychology
Show HN: Principles of Building AI Agents book [pdf]
github.com·18h·
Discuss: Hacker News
🤖AI
A Few Words Can Distort Graphs: Knowledge Poisoning Attacks on Graph-based Retrieval-Augmented Generation of Large Language Models
arxiv.org·4h
🤖AI