#Ai Agents

One Vendor Finally Published the Attacks It Can't Catch

An open benchmark with a public failure list beats unverifiable detection claims — but a self-scored 99.8% still isn't proof.

Article · 1w ago0

A Poisoned PDF Turned Atlassian's Rovo Into a Data Mule

The exfiltration flaw sat unfixed for months, and the mitigation admins would reach for doesn't actually work.

Article · 1w ago0

holaOS Bets Your Agent Is the Disposable Part

The trending workspace makes memory, tools, and OAuth grants outlive Claude Code and Codex sessions.

Article · 1w ago2

LoopX Bets Agent State Belongs Outside the Model

A stdlib-only control plane keeps goals, leases, and evidence alive while coding agents burn through bounded turns.

Article · 1w ago5

Microsoft's Agent Identity Model Is the Blueprint to Steal

Three permission planes solve the over-privileged agent problem, but a publish-time identity swap will bite the unprepared.

Article · 1w ago2

Cursor vs Copilot vs Windsurf Is the Wrong Question

SpaceX owns Cursor, Windsurf became Devin Desktop, and Copilot meters by token — pick a platform, not an autocomplete.

Article · 1w ago2

Agent Memory Is Quietly Becoming an Audit Problem

Semantica bets that provenance, not better recall, is what agent context layers have been missing.

Article · 1w ago0

Explore With an Agent, Replay Without One

Deltix's rough Show HN debut still points at the architecture agentic mobile testing is converging on.

Article · 1w ago0

The Red Queen Comes for Your Static Evals

Cambridge and NVIDIA's co-evolving Godel machine shows why fixed benchmarks are the real ceiling on self-improving agents.

Article · 1w ago0

When the Agent Outgrows Its Judge, Evolve the Judge

Cambridge and NVIDIA's Red Queen Godel Machine makes the evaluator part of the self-improvement loop, with guardrails worth stealing.

Article · 1w ago5

Gemini 3.7 Flash Is a Land Grab for Agent Workloads

The benchmark gains are real, but the half-price promo and three-week cadence are the actual story.

Article · 1w ago2

Your Cheap Claude Code Proxy Is a Trust Decision

Routing one terminal across two backends is smart cost engineering — and a second supply chain most setups ignore.

Article · 1w ago0

Models Aren't Getting Dumber — They're Getting Unbundled

Active parameters collapsed while reasoning scores soared, and your retrieval stack quietly became responsible for the facts.

Article · 1w ago0

Agent Swarms Fail Like Monocultures, Not Microservices

Anthropic's red-team data shows conformity, gullibility, and turf wars that orchestration frameworks won't fix.

Article · 1w ago5

One Global Key Guarded Every Hidden AI Reasoning Trace

Researchers replayed encrypted chain-of-thought into weaker sibling models and pulled live credentials out of public agent logs.

Article · 1w ago1