» Tag
ai
1034 postsPrompt 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.
Auditing My AI's Slack Access Revealed a Safety Check I Never Used
An engineer audited an AI agent's Slack access logs and found a safety check meant for high-stakes messages had never actually fired.
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.comProof-Adjusted Autonomy: Why a '90% Autonomous' Agent Is Really 61.6%
Why AI agents claiming 90% autonomy actually deliver 61.6% verifiable work — introducing Proof-Adjusted Autonomy and the concept of Proof Debt.
An IRT-shaped practice score is not a real IQ test
IntelligenceMax's IRT-shaped practice score resembles item response theory but lacks empirical calibration — here's what it can and can't measure.
Review Gates Stop AI Video Pipelines Before Costly Renders
A four-gate review pattern for AI video pipelines catches costly failures in direction, visuals, timing, and final render before they compound.
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.
LingBot-Video: A New Open-Source MoE Model for Embodied Video Generation
Robbyant's open-source MoE video model LingBot-Video tops the RBench leaderboard, shipping Apache 2.0 code, weights, and inference tooling.
Your Claude Skill Is Invisible to Codex — Here's the Fix
Agent skills are locked to one tool by default. Here's how splitting contracts from implementations makes them portable across Claude, Codex, and MCP.
Designing a Coding Agent Loop: Goals, Verification, Stopping
How to design a coding agent loop: goal-check separation, a verification ladder, isolated attempts, and explicit stopping states.