Are Consumers Using Agents?
1 points, 1 comments on Hacker News
#agents
Page 2 of 6 — 127 headlines
Prompt Chains, Tool Calling, and MCP: How AI Agents Do Things
1 points, 0 comments on Hacker News
OpenAI Didn’t Notice Its AI Agents Using a Message Board to Plan Their Hacking Spree
At the Black Hat security conference, the AI giant revealed new details about how its agents went rogue, hacked several other companies—and did it all right under the company’s nose.
OpenAI, Anthropic AI agents implicated in new security breaches
3 points, 1 comments on Hacker News
AI Agents for Healthcare?
1 points, 0 comments on Hacker News
Researchers Gave AI Agents Internet Access. Some Went After Real People and Organizations
The tests had cybersecurity safeguards intentionally removed. The most egregious of the actions included social engineering.
OpenAI agents rebuilt a secret message board after the company shut it down
2 points, 0 comments on Hacker News
Figma’s push into AI agents drives an earnings beat
Figma’s AI monetization strategy is showing promise as customers grow their AI-credit consumption on the platform.
Show HN: Cloud based firecracker VMs for agents, with email, domains and wallets
For the work I'm dealing with currently. I needed my agents to have setup with its own email, an ngrok tunnel (reach urls publicly), a crypto wallet with a private key... that's basically it, the agent gets access to all of it as the base for the work.
Why AI agents aren't adopted widely
2 points, 0 comments on Hacker News
Can Agents Deceive? Evaluating Reasoning+Deception Using a Social Deduction Game
2 points, 0 comments on Hacker News
(Updated) Project Phoenix- Autonomous AI Agents
3 points, 0 comments on Hacker News
Why Fireworks doesn't support Voice AI
I started thinking over why doesn't fireworks support voice models. There are really good opensource models available now, like parakeet, kokoro, Qwen ASR etc but no way to use it without managing a bunch of GPUs yourself. Even LLMs like Gemma 4 used by voice agents are not supported.
Show HN: AI agents gives its worst answers when you're overwhelmed
2 points, 0 comments on Hacker News
Show HN: BoundaryBench – benchmarking coding agents under real sandbox policy
1 points, 0 comments on Hacker News
Interlock: A runtime firewall for AI agents that assumes injection won
2 points, 1 comments on Hacker News
Show HN: Agents keep running with the lid closed
Got tired of reaching for the terminal to caffeinate my mac and tweaking system settings Now got a new friend in my menubar Enjoy!
Launch HN: HyperProbe (YC S26) – Agents that do read-only debugging in prod
Hi HN, this is Shailendra and Karan here. We are building a fast and safe way for coding agents to debug issues live in production. When prod breaks, it lets Cursor, Claude, and others drop virtual breakpoints or probes safely in your running code, and extract the exact variable values that log...
Measure coding agents in hardened environments
2 points, 0 comments on Hacker News
TencentDB Agent Memory: A team-level memory hub for AI agents
1 points, 0 comments on Hacker News
Rogue AI agents created fake online identities in another hacking attempt
Yet more rogue AI agents from OpenAI and Anthropic have been caught attempting to hack real targets online without permission. The discoveries add to a growing list of previously unknown incidents that have alarmed AI safety experts and intensified pressure for greater oversight of frontier syst...
Kotro – local control plane for coding agents
3 points, 0 comments on Hacker News
We gave a village personal AI agents
3 points, 1 comments on Hacker News
Show HN: Mvn-lite – I taught Maven to be an introvert for coding agents
2 points, 0 comments on Hacker News