
Tim Yardley
@timyardley
Followers
1K
Following
108
Media
110
Statuses
15K
husband, father, security researcher. All thoughts and opinions are my own.
Champaign, Illinois
Joined February 2009
Minusx | What makes Claude Code so damn good (and how to recreate that magic in your agent)!?
minusx.ai
Claude Code is the most delightful AI agent/workflow I have used so far. Not only does it make targeted edits or vibe coding throwaway tools less annoying, ...
0
0
0
Six Principles for Production AI Agents --
app.build
Practical lessons from building production agentic systems
0
0
0
The Big LLM Architecture Comparison
magazine.sebastianraschka.com
From DeepSeek-V3 to Kimi K2: A Look At Modern LLM Architecture Design
0
0
0
MCP Security Vulnerabilities and Attack Vectors | Forge Code
forgecode.dev
A deep dive into critical security vulnerabilities found in Model Context Protocol (MCP) implementations, including tool description injection, authentication weaknesses, and supply chain risks,...
0
0
2
Google’s latest AI security announcements --
blog.google
Here’s what we’re announcing at cybersecurity conferences like Black Hat USA and DEF CON 33.
0
0
0
Cyberattack deals blow to Russian firmware used to repurpose civilian drones for Ukraine war | The Record from Recorded Future News
therecord.media
The developers behind a custom firmware used to convert consumer drones for military use in Ukraine have reported a cyberattack disrupting the system that distributes the software.
0
0
0
XBOW – The road to Top 1: How XBOW did it
xbow.com
For the first time in bug bounty history, an autonomous penetration tester has reached the top spot on the US leaderboard.
0
0
0
Local Privilege Escalation via host option | Sudo
sudo.ws
Sudo’s host (-h or --host) option is intended to be used in conjunction with the list option (-l or --list) to list a user’s sudo privileges on a host other than the current one. However, due to a...
0
0
0
Critical RCE in Anthropic MCP Inspector (CVE-2025-49596) Enables Browser-Based Exploits | Oligo Security
oligo.security
A critical Remote Code Execution flaw (CVSS 9.4) in Anthropic’s MCP Inspector exposes AI developers to browser-based attacks via 0.0.0.0 and DNS rebinding. Learn how CVE-2025-49596 was exploited from...
0
0
0
The New Skill in AI is Not Prompting, It's Context Engineering --
philschmid.de
Context Engineering is the new skill in AI. It is about providing the right information and tools, in the right format, at the right time.
0
0
0
Huawei’s 3,000km solid-state battery patent with 5-minute charge ignites industry race
carnewschina.com
Huawei’s patent filing describes a sulfide-based solid-state battery targeting higher energy density and reduced charging time
0
0
0
China Is Studying How to Hack and Crash Our Power Grids
linkedin.com
power grid, china, solar, cyberattack, cybersecurity, Huawei, Sungrow, hack, cyber attack, killswitch, kill switch, BESS, solar cybersecurity, DER
0
0
0
MiniMax_M1_tech_report [pdf] - open weight large scale hybrid attention reasoner
github.com
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. - MiniMax-AI/MiniMax-M1
0
0
0
US intelligence taps AI for chatbots, JFK file review • The Register
theregister.com
: Plus: AWS launches second Secret-level cloud region
0
0
0
Trump team leaks AI plans in public GitHub repository • The Register
theregister.com
Updated: The AI.gov repository and staging site vanished when we asked questions, but don't worry – we captured backups
0
0
0
A look at CloudFlare’s AI-coded OAuth library – Neil Madden
neilmadden.blog
I decided today to take a look at CloudFlare’s new OAuth provider library, which they apparently coded almost entirely with Anthropic’s Claude LLM: This library (including the schema do…
0
0
0
Cellebrite to acquire mobile testing firm Corellium in $200 million deal | CyberScoop
cyberscoop.com
Both companies have faced controversy in recent years, primarily for their work in circumventing mobile device security features
0
0
0