» Tag
llm
535 postsHow Guided Determinism Balances Autonomy and Reliability in AI Agents
Enterprise AI architecture combining Agent Graph orchestration and guided determinism to balance LLM autonomy with workflow reliability.
When Claude Couldn't See: AI Confabulation on Explicit Content
Claude misread an explicit image as a toddler photo, exposing how AI content guardrails are trained into model weights rather than applied as filters.
Wattage: An Offline Token-Cost Profiler and CI Gate for AI Agents
Wattage profiles AI agent token spend from OTel traces, prices waste in dollars, and gates CI on cost regressions — open-source and offline.
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.comQuantprobe Runs a 110B-Parameter LLM on a 16GB RAM 2016 Desktop
Quantprobe shows how careful memory-tier placement lets a 2016 desktop with 16GB RAM run a 110B-parameter LLM, validated with pre-registered predictions.
How Netflix Runs Its Own LLM Serving Stack with vLLM and Triton
Netflix engineers explain how they built an in-house LLM serving stack using vLLM, Triton, and an OpenAI-compatible API, with real production lessons.
Governed Agent: LLM reads text, code and rules decide outcomes
Governed Agent demonstrates a deterministic architecture where an LLM only extracts text while code and tables decide outcomes, using ITIL as the example.
Beyond Context Engineering: A Discipline for Reliable LLMs
A position paper argues LLM reliability requires channel engineering, not just context engineering, and introduces the Socium collaboration model.
600 AI Architectures: What LLMs Default to When Designing Systems
Six LLM families produced 600 system architectures from identical briefs, exposing default tech choices, low consensus in key layers, and constraint-driven shifts.
AVE: A Behavioral Vulnerability Standard for Agentic AI
AVE is a new standard classifying behavioral vulnerabilities in agentic AI, using AIVSS scoring and the bawbel-scanner reference tool for CI checks.
AI-Assisted Vacation Project Cracks Open 2008 Quantum Physics Puzzle
An engineer used Claude AI on vacation to solve two open corners of a 2008 quantum mechanics constraint problem, verified via exact arithmetic.