🤖 AI - robbie3005205230 · Scour

LLM Observability with Self-Hosted Langfuse and vLLM 🧠LLMs

pyimagesearch.com·2d

AI researchers flag bias risks in LLM judging 🧠LLMs

kite.kagi.com·5d

Architecting LLM Agents: The SDB Primitive 🕵️AI Agents

startuphub.ai·7h

AI and LLM Whitepaper Excerpts · Gravity7 🧠LLMs

whitepapers.gravity7.com·2h

BoLT: A Benchmark to Democratize Black-box Optimization Research for Expensive LLM Tasks 🧠LLMs

LLM Wiki v2 — extending Karpathy's LLM Wiki pattern with lessons from building agentmemory 🧠LLMs

gist.github.com·23h·Hacker News

LLM Inference 🧠LLMs

iop.systems·1h

8 Architectural Pillars to Boost GenAI LLM Accuracy and Performance in Low Cost 🧠LLMs

techcommunity.microsoft.com·4d

LLM Evaluation and AI Observability for Agent Monitoring 🧠LLMs

blog.jetbrains.com·1d

Does Your Project Need an LLM, Machine Learning or Statistics? 🤖Machine Learning

builtin.com·8h

The David and Goliath Paradigm: Comparing Small and Large Language Models 🧠LLMs

hpcwire.com·8h

Global Trends Overview: The Rapid Evolution of the Large Language Model (LLM) Market in Content Creation 🧠LLMs

MukundaKatta/llm-circuit-breaker: Tiny circuit breaker for LLM API calls. Pairs with llm-retry: retry handles transient failures, breaker stops calling when provider is down. Thread-safe, async-runtime-agnostic. ✍️Prompt Engineering

github.com·2h·DEV

Development/AI policy ⚙️Automation

wiki.documentfoundation.org·4d

Four-Tier Memory Hierarchy for LLM Reasoning (USC, UW) 🧠LLMs

semiengineering.com·10h

LLM Tool Calling ⚙️Automation

dsebastien.net·2d

Learnings from 100K lines of Rust with AI (2025) ✍️Prompt Engineering

news.ycombinator.com·12h·Hacker News

tokenspeed — feel LLM tokens-per-second 🧠LLMs

mikeveerman.github.io·43m

LLMs are functions, not brains. 🧠LLMs

james-pritchard.com·2d

Building Type-Safe LLM Agents With Pydantic AI: Setting Up & Getting Structured Output From LLMs 🧠LLMs

youtube.com·6d

Log in to enable infinite scrolling