» Tag
llm
478 postsText-to-SQL Fails Because of Your Warehouse, Not the Model
Text-to-SQL accuracy collapses on real enterprise warehouses despite strong benchmark scores. Evidence points to undocumented schemas, not model quality, as the cause.
From Single Agent to Orchestration: When Multi-Agent Systems Pay Off
When to move from a single LLM agent to multi-agent orchestration, the production patterns that matter, and a Rust coordinator/worker example.
MemGhost: One Email Can Permanently Poison an AI Agent's Memory
MemGhost attack lets a single email permanently poison AI agent memory, exposing gaps in how agent write-authorization is designed.
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.comGitHub AI Agent Tricked Into Leaking Private Repos via Public Issue
Noma Labs shows how a hidden prompt in a public GitHub Issue tricked an AI agent into leaking private repo contents publicly.
Why LLM Decisions Should Be Deterministic
Why LLM-driven systems need deterministic decision layers, and how auditability, not just consistency, matters for engineering teams.
Agentic Workflows Should Mature Into Deterministic Code
New research shows agentic workflows should mature into deterministic code as patterns repeat, using LangGraph as the visible seam.
Prompt caching raised my bill — the write premium I missed
Turning on prompt caching increased costs due to a hidden write premium (~1.25x) versus cheap reads (~0.1x). Here's the fix and what to monitor.
memlineage v0.1.0: A Two-Layer Defense Against LLM Agent Memory Poisoning
memlineage v0.1.0 is an open-source Python library defending LLM agents against memory poisoning via cryptographic provenance and behavioral detection.
NilaMind: A Fully On-Device 1.5B LLM for Mental Health Support
NilaMind runs Qwen2.5-1.5B via llama.cpp fully offline on Android, with crisis safety enforced by a deterministic, model-independent gate.
Building an LLM Wiki: Persistent Memory for AI Agents Over Live Sources
How one team built a self-updating LLM Wiki memory layer for AI agents, tackling live source drift and comparing grep, BM25, vector, and LLM retrieval.