Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
…The platform through which they access the model (such as an API or an agentic coding platform like Claude Code) also has no bearing on how high-risk their actions are. What…
Search
Related topics:
Claude
All sources
anthropic.com
30
xda-developers.com
27
theregister.com
10
developer.nvidia.com
5
blog.cloudflare.com
4
cloud.google.com
2
engadget.com
2
bleepingcomputer.com
2
neowin.net
2
tomsguide.com
2
theverge.com
2
wired.com
2
Top stories
I ignored Claude Code sub-agents until my context window started collapsing
2d agoAnnouncing Claude apps gateway for Google Cloud | Google Cloud Blog
4d agoNVIDIA BioNeMo Agent Toolkit Brings Accelerated AI to Life Sciences Researchers in Claude Science
5d agoAI coding agents can be tricked into installing malware via 'clean' GitHub repositories — Mozilla's 0din team shows how Claude Code can be exploited by its own helpfulness
1w agoProduct Archives
…The agent awakens Introducing agent mode for GitHub Copilot in VS Code, announcing the general availability of Copilot Edits, and providing a first look at our SWE agent. Announcing 150M developers and…
Streaming Tokens and Tools: Multi-Turn Agentic Harness Support in NVIDIA Dynamo | NVIDIA Technical Blog
…architecture underneath agentic inference: the frontend, router, and KV cache management. This follow-up focuses on correctness, user-experience equivalence, and performance. Agentic harnesses are still evolving quickly. Claude Code, Codex, and…
Treating Claude Code as just a coding tool is like using a Swiss Army knife to open cans
…I now think of it more as a context-aware terminal agent, which also happens to be great at coding. Claude Code excels at a lot of tasks for the same reason…
Discussions and forums
Show HN: Deconstructing Anthropic's Coding Agent Control Model
Anthropic recently published an excellent write-up on how they contain Claude Code and its sub-agents.One thing that stood out is that the architecture isn’t really about Claude—it describes a general pattern for securin…
1
Show HN: Agentspace – long-running YOLO agent sessions in Docker
Hi HN, I built agentspace because I kept seeing tmux recommended for keeping Claude Code sessions alive over SSH. I find multiplexers painful because they subtly change shell behavior in ways I always forget. They also d…
5
2
Show HN: Better Graphs – Teach agents to stop making plain Matplotlib slop
https://github.com/temataro/better-graphsI want to teach good Matplotlib taste to agents and humans. This repo contains: 1. Agent instructions + design motifs (Claude Code skills + a CLAUDE.md). 2. An online "blog" tutor…
6
1
Show HN: RTFRA - A Humble Proposal [RFC]
You know that feeling when no one reads the documentation you wrote? I bet we've all experienced that moment when, after spending a lot of time crafting a README file, you realize nobody gives a fuck.But how do you know …
1
1
Show HN: AVP – an agent can't leak a secret it never had
A process can't leak a secret it never had.Shai-hulud, prompt-injection - you name it. They cannot steal what your agent (or an process) don't have.I run coding agents (Claude Code, Codex) on my own machines most of the …
3
Demystifying evals for AI agents
…For example, Claude Code is a flexible agent harness, and we used its core primitives through the Agent SDK to build our long-running agent harness . An evaluation suite is a collection…
Anthropic confirms it leaked the source for Claude Code, blames human error
…Anthropic's Claude Mythos found 271 Firefox vulnerabilities - CTO calls it just as capable as 'elite security researchers' Google is readying Gemini for a 24/7 personal AI agent Google finds hackers…
I tried PewDiePie's open-source AI workspace, and it's weirdly great
…Look at Open Design for example - Claude Design dropped, I blinked, and Open Design suddenly appeared as a direct alternative you can use locally. I've been experimenting with local AI most…
I let Claude manage my DNS server, and it taught me more than years of documentation
…Or an agent watching logs for suspicious patterns, and automatically adjusting blocklists. After all, LLMs are supposed to be about making things easier for the user, without needing my input. Technitium was…
I built the same app with Claude Design and its open-source rival, and the winner wasn't close
…That brought design to people who were already in Claude for something else entirely, and probably nudged a few would-be Claude Design users into paying for the rest of the suite…
Claude Skills changed how I work — 5 ways I use them every day
…containing a file called SKILL.md . The top of that file needs two things: a name and a description. The description is the most important sentence you'll write, because Claude uses…