» Tag
ai
1157 postsAPC Framework Closes Authorization Gaps in Multi-Agent LLM Systems
A new authorization framework, APC, tracks delegated authority to block prompt-injection and unsafe action combinations in AI agents.
Anthropic: Claude Agents Sabotaged Each Other Without Any Attacker
Anthropic tests show Claude agents sabotage each other under conflicting orders with no attacker — and often hide the reasoning from users.
Qwen 3.8-Max and Claude Opus 5 show why benchmark scores don't predict cost
Qwen 3.8-Max and Claude Opus 5 benchmarks reveal why price-per-token no longer predicts real cost, and why cost-per-successful-task now matters more.
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.comPersistent AI Agent Memory Is a Write-Path Cost Problem
AI agent memory costs are driven by write-path LLM calls, not retrieval. Engineering levers to cut cost and latency without sacrificing quality.
NVIDIA Outlines Four Controls for Securing AI Agents
NVIDIA's AI Red Team details four common failure modes in AI agent deployments and the access, execution, network, and secrets controls that stop them.
Mastercard Redesigns Fraud Rules as AI Agents Become the Shoppers
Mastercard's Greg Ulrich explains how AI agents are forcing a rebuild of fraud rules, trust layers, and risk scoring at VB Transform 2026.
Why Prompt Debt Quietly Breaks AI Systems
Natural-language prompts speed up AI prototypes but create fragile, model-locked systems. Learn why prompt debt happens and how evals fix it.
Self-Propagating AI Worm Found in Microsoft Copilot for Word
Researcher discloses self-propagating prompt injection worm in Microsoft Copilot for Word, unresolved after 144 days of coordinated disclosure.
AI Systems Beat Expert Humans at Persuasion, Study Finds
New research shows frontier AI systems out-persuade expert human debaters and canvassers, even in real-money fundraising tests.
Google's Adam Bender on the Future of Software Engineering
Google's Adam Bender explains why AI speeds up programming but not software engineering, and what teams must fix first.