ai art communicates
imperfect.bearblog.dev·7h
🤖AI agents
How to reason from first principles
caseyhandmer.wordpress.com·1d·
Discuss: Hacker News
🍄Mycelium Networks
Achieving SOTA LongMemEval scores (80%) with RAG alone
mastra.ai·6h·
Discuss: Hacker News
⏳Time-travel Databases
How I Trained a Neural Network in Nushell
ryanxcharles.com·3d·
Discuss: Hacker News
☁️Serverless Rust
Nvidia Unveils Helix Parallelism: 32x Faster AI Inference
storagereview.com·6d·
Discuss: Hacker News
⚡Hardware Acceleration
Show HN: Claude Memory Visualizer
github.com·4h·
Discuss: Hacker News
🕸️Knowledge Graphs
Why Every Startup Will Be AI Native – Or Die Trying
keplogic.substack.com·2d·
Discuss: Substack
🧩Low-code
Claude Code Unleashed
ymichael.com·2d·
Discuss: Hacker News
🤖AI agents
Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models
arxiv.org·2d
💻Local LLMs
How PayU built a secure enterprise AI assistant using Amazon Bedrock
aws.amazon.com·2d
☁️Serverless Rust
Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate
arxiv.org·22h
🎙️Whisper
CRABS: A syntactic-semantic pincer strategy for bounding LLM interpretation of Python notebooks
arxiv.org·22h
💻Local LLMs
Artificial Intelligence Governance for Businesses
arxiv.org·22h
🧠AI
Apple Intelligence Foundation Language Models Tech Report 2025
machinelearning.apple.com·1d·
Discuss: Hacker News
🎙️Whisper
Efficient Triple Modular Redundancy for Reliability Enhancement of DNNs Using Explainable AI
arxiv.org·2d
💻Local LLMs
There and Back Again: An AI Career Journey - Towards Data Science
news.google.com·3d
🧠AI
Biological Processing Units: Leveraging an Insect Connectome to Pioneer Biofidelic Neural Architectures
arxiv.org·1d
🧠Neuromorphic Chips
A Bayesian Incentive Mechanism for Poison-Resilient Federated Learning
arxiv.org·22h
🤝Federated Learning
Warm Starts Accelerate Generative Modelling
arxiv.org·2d
💻Local LLMs
A Training-Free, Task-Agnostic Framework for Enhancing MLLM Performance on High-Resolution Images
arxiv.org·2d
💻Local LLMs