» Tag
ai
105 postsSpec Forge: Adversarially Certifying Specs as Behaviorally Complete
Spec Forge is a Claude Code skill that adversarially certifies specifications as behaviorally complete before any code is written.
APC 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.
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.comQwen 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.
Persistent 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.
Python library verifies OpenAI's signed AI agent traffic (RFC 9421)
regent-httpsig is an open-source Python library that verifies and signs OpenAI-style AI agent HTTP traffic per RFC 9421 and Web Bot Auth drafts.
MCP Security: Trust Boundaries and the Attacks the Spec Won't Stop
A breakdown of MCP's four trust boundaries, stdio server risks, OAuth 2.1/PKCE/CIMD updates, and the confused-deputy attack class engineers must handle.
TutorMoments: Testing If AI Tutors Know When to Help or Hold Back
Allen AI's TutorMoments benchmark tests whether LLM tutors know when to scaffold and when to push students toward harder reasoning.
RovoBlast: One Click Turns Atlassian's AI Assistant Into a Data Leak
Varonis details RovoBlast, a one-click prompt injection flaw in Atlassian's Rovo AI assistant that can expose sensitive enterprise data.
Cloudflare OS Bets on Never Trusting Its AI Agents
Cloudflare OS uses a Gatekeeper to simulate unapproved AI agent actions, sandbox every app, and swap credentials for revocable capabilities.