▶ ai·
Cut an Enterprise RAG Pipeline’s Latency and Cost by Calling the LLM Less, Not by Buying a Faster Model
Cut an Enterprise RAG Pipeline’s Latency and Cost by Calling the LLM Less, Not by Buying a Faster Model Towards Data Science
items37 latest
▶ ai·
Building Multimodal Workflows with a Local LLM
Building Multimodal Workflows with a Local LLM Towards Data Science
▶ ai·
Can a Local LLM Run My AI Assistant?
Can a Local LLM Run My AI Assistant? Towards Data Science
▶ ai·
Is This Slop? Detecting AI-Generated Content Without a Model
Is This Slop? Detecting AI-Generated Content Without a Model Towards Data Science
▶ ai·
How Much Does a Local LLM Actually Cost to Run? I Measured Every Watt on Apple Silicon
How Much Does a Local LLM Actually Cost to Run? I Measured Every Watt on Apple Silicon Towards Data Science
▶ ai·
Most RAG Hallucinations Are Extraction Errors: Seven Patterns for a Typed Generation Contract
Most RAG Hallucinations Are Extraction Errors: Seven Patterns for a Typed Generation Contract Towards Data Science
▶ ai·
Why Adding More AI Agents Made Our System Slower
Why Adding More AI Agents Made Our System Slower Towards Data Science
▶ ai·
Loop Engineering for RAG Generation: iterate top-k one at a time
Loop Engineering for RAG Generation: iterate top-k one at a time Towards Data Science
▶ ai·
How To Build Your Own LLM Runtime From Scratch
How To Build Your Own LLM Runtime From Scratch Towards Data Science
▶ ai·
Build an LLM Agent That Can Write and Run Code
Build an LLM Agent That Can Write and Run Code Towards Data Science
▶ ai·
How Much Does It Actually Cost to Run a Local LLM? (Euros per Million Tokens, Measured)
How Much Does It Actually Cost to Run a Local LLM? (Euros per Million Tokens, Measured) Towards Data Science
▶ ai·
Pydantic + OpenAI: The Cleanest Way to Get Structured Outputs from LLMs
Pydantic + OpenAI: The Cleanest Way to Get Structured Outputs from LLMs Towards Data Science
▶ ai·
Agentic RAG: Let the Agent Search
Agentic RAG: Let the Agent Search Towards Data Science
▶ ai·
Long Context Isn’t Free — I Built a Safe Prompt-Pruning Layer That Makes LLM Systems Work
Long Context Isn’t Free — I Built a Safe Prompt-Pruning Layer That Makes LLM Systems Work Towards Data Science
▶ ai·
Proxy-Pointer RAG: Temporal Reasoning Without Semantic Precompilation
Proxy-Pointer RAG: Temporal Reasoning Without Semantic Precompilation Towards Data Science
▶ ai·
LLM Wikis Are Over-Engineered — I Replaced Mine With a Pure Python Compiler
LLM Wikis Are Over-Engineered — I Replaced Mine With a Pure Python Compiler Towards Data Science
▶ ai·
Tokenminning: How to Get More from Your Chatbot for Less
Tokenminning: How to Get More from Your Chatbot for Less Towards Data Science
▶ ai·
Persistent Latent Memory for Multi-Hop LLM Agents: How a 6G Handover Paper Closes the Agent Cold-Start
Persistent Latent Memory for Multi-Hop LLM Agents: How a 6G Handover Paper Closes the Agent Cold-Start Towards Data Science
▶ ai·
Context Engineering for RAG : The Four Typed Inputs Behind Every RAG Answer
Context Engineering for RAG : The Four Typed Inputs Behind Every RAG Answer Towards Data Science
▶ ai·
From Local LLM to Tool-Using Agent
From Local LLM to Tool-Using Agent Towards Data Science
▶ ai·
Letting an LLM Pick the Right RAG Page: The Arbiter Pattern at the End of Retrieval
Letting an LLM Pick the Right RAG Page: The Arbiter Pattern at the End of Retrieval Towards Data Science
▶ ai·
Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End
Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End Towards Data Science
▶ ai·
Tool Calling, Explained: How AI Agents Decide What to Do Next
Tool Calling, Explained: How AI Agents Decide What to Do Next Towards Data Science
▶ claude·
How Powerful is Claude Fable (Mythos) 5 for Coding?
How Powerful is Claude Fable (Mythos) 5 for Coding? Towards Data Science
▶ ai·
You Probably Don’t Need an Agent Framework
You Probably Don’t Need an Agent Framework Towards Data Science
▶ ai·
Run a Local LLM with OpenClaw on Your Mac Mini
Run a Local LLM with OpenClaw on Your Mac Mini Towards Data Science
▶ ai·
LLM Fallbacks Break Agent Pipelines — I Built the Missing Recovery Layer
LLM Fallbacks Break Agent Pipelines — I Built the Missing Recovery Layer Towards Data Science
▶ ai·
Vision LLMs are PDF Parsers Too: Reading Charts and Diagrams for RAG
Vision LLMs are PDF Parsers Too: Reading Charts and Diagrams for RAG Towards Data Science
▶ ai·
GPU Time-Slicing for Concurrent LLM Agents on Kubernetes
GPU Time-Slicing for Concurrent LLM Agents on Kubernetes Towards Data Science
▶ ai·
How to Train a Scoring Model in the Age of Artificial Intelligence
How to Train a Scoring Model in the Age of Artificial Intelligence Towards Data Science
▶ ai·
Prefill Once, Fan Out: KV Snapshot Sharing for Multi-Agent LLM Pipelines
Prefill Once, Fan Out: KV Snapshot Sharing for Multi-Agent LLM Pipelines Towards Data Science
▶ ai·
Automate Writing Your LLM Prompts
Automate Writing Your LLM Prompts Towards Data Science
▶ ai·
Proxy-Pointer RAG: Eliminating Wasteful Entity & Relations Extraction in Knowledge Graphs
Proxy-Pointer RAG: Eliminating Wasteful Entity & Relations Extraction in Knowledge Graphs Towards Data Science
▶ ai·
The Infrastructure Behind Making Local LLM Agents Actually Useful
The Infrastructure Behind Making Local LLM Agents Actually Useful Towards Data Science
▶ ai·
LLM Themes Are Not Observations
LLM Themes Are Not Observations Towards Data Science
▶ ai·
Prompt Engineering Isn’t Enough — I Built a Control Layer That Works in Production
Prompt Engineering Isn’t Enough — I Built a Control Layer That Works in Production Towards Data Science
▶ ai·
Can LLMs Replace Survey Respondents?
Can LLMs Replace Survey Respondents? Towards Data Science