» Tag
llm
478 postsLLM-as-Judge: Use Binary Checks for Evidence, Not Aggregate Scores
Explore the benefits of using binary checks and a single verdict in LLM evaluations. A reliable quality assessment method for engineers.
Vercel AI SDK 6's Agent Is Really Just a while Loop
A hands-on breakdown of how AI SDK 6's ToolLoopAgent and stopWhen actually control the agent loop, tested with a deterministic mock model.
Ghost Vessel Gives a Local AI Agent a Face Instead of a Chat Box
A developer swapped his local LLM chat interface for a video-call-style avatar. Ghost Vessel uses pre-rendered clips and emotion tags to stay GPU-free, and is open source.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comAnthropic Discovers a Global Workspace Inside Language Models
Anthropic's new J-lens technique uncovers an internal region in Claude-like models that behaves like the brain's global workspace of consciousness.
Why You Need a Smoke Test Before Switching LLM Providers
Sending one prompt isn't enough before swapping LLM providers. A 10-minute smoke test covering timeouts, streaming, rate limits, and tool-call retry safety.
Multi-Agent Architecture Patterns for Real-World Financial Systems
Engineering patterns for safely deploying LLM agents in African microfinance systems: bounded authority gates, bias audits, and shared-state coordination across agent pipelines.
LLM agents are breaking 20-year-old web architecture
Stateful LLM agents are exposing cracks in the stateless-server-plus-database web architecture. The missing piece: a routing primitive that can address running processes directly.
Cruxible: An Open-Source Governed Truth Layer for AI Agents
Cruxible replaces unreliable text-based memory for AI agents with a deterministic, auditable state layer. Open-source, Apache-2.0 licensed, built with Python and SQLite.
An Open Agent Security Benchmark: Uncaught Attacks
An open benchmark featuring 497 attacks targeting modern LLM agents has been established.
Context Engineering in LLM Applications
Context engineering optimizes LLMs with domain knowledge for better performance. It uses an index for more accurate responses.