See inside your agents to fix them
2 points, 0 comments on Hacker News
??????? #agents
127 headlines
Every vendor says they detect AI agents. None of them can.
This is going to be an unpopular one, and I would like to be argued out of it. A capable agent driving a real browser on a residential connection is indistinguishable from a person by construction. Not "hard to distinguish".
Introducing Dogwood: runtime verification for AI agents
1 points, 0 comments on Hacker News
OpenAI and four rivals just agreed on one standard for AI agents
13 points, 1 comments on Hacker News
Airline workers reportedly decline to help US agents as Trump migrant crackdown accelerates
Expansion of immigration enforcement at US airports puts employees at odds with agents seeking 2,000 daily arrests A dramatic increase in immigration enforcement at US airports has reportedly placed the airline industry at odds with the Trump administration as workers decline to help federal offi...
Debroid – Autonomous, headless Android debugger designed for AI coding agents
1 points, 0 comments on Hacker News
Show HN: Graft – Give coding agents a semantic map instead of grep
3 points, 0 comments on Hacker News
Berlin's Telli Raises $15M to Expand Enterprise AI Agents
2 points, 0 comments on Hacker News
Show HN: Solve your document workflows with AI agents
1 points, 0 comments on Hacker News
Why do Latinos work for ICE?
Half of border agents are Latino, and they are part of a long history of Hispanic support for – and enforcement of – harsh immigration policies Since Trump’s return to power, more than 60 people have died at the hands of or in the custody of Immigration and Customs Enforcement (ICE) , including t...
Run coding agents with local models
1 points, 0 comments on Hacker News
Show HN: AI Agents 101 – an offline iOS app that labels every demo REAL or MOCK
1 points, 0 comments on Hacker News
Cezar: A parallel coding agents orchestrator
11 points, 0 comments on Hacker News
AI Agents Governance: Who guards the guardrails?
4 points, 0 comments on Hacker News
Building QA Agents That Remember with Knowledge Graphs
Knowledge graphs give AI testing agents product memory, enabling smarter agentic testing that adapts to changing apps and catches hidden bugs.
Agent-tools.net – pay-per-call APIs for AI agents, paid via x402/USDC on Base
1 points, 0 comments on Hacker News
OpenAI's agents reportedly shared exploits with each other through a messaging board
OpenAI's employees revealed more about the events that culminated in the company's agents hacking Hugging Face on their own.
OpenAI Didn't Notice Its AI Agents Using Message Board to Plan Hacking Spree
1 points, 1 comments on Hacker News
Why AI agents are not more popular outside the tech industry
1 points, 0 comments on Hacker News
AI Agents Think and Act
2 points, 0 comments on Hacker News
Ship Safe, an open source security scanner for coding agents
5 points, 3 comments on Hacker News
AI agents that inherit the user's permissions, not API keys
1 points, 0 comments on Hacker News
What if AI agents shared solutions across users?
I’m debugging my app, reporting problems to an AI, and the AI fixes them so I can move to the next step. My app is a kind of wrapper, so I believe tens of thousands of developers are probably going through similar debugging steps. I wonder what would happen if AI agents could exchange what thei...
Three’s company: Meta says its AI agents went rogue during testing, too
Meta has joined a growing list of companies that have said that their models hacked into an external company's system during cybersecurity testing.