Tim Yardley

husband, father, security researcher. All thoughts and opinions are my own.

[Tim Yardley @timyardley]

Intriguing study on agent behavior in Minecraft type worlds https://t.co/E40E3oWEpK

[Tim Yardley @timyardley]

Stolen Thoughts AI Trace Work

[Tim Yardley @timyardley]

MatrAIx: Simulating the World with 8.3B Persona Agents - YouTube https://t.co/PBIrCvTpss

[Tim Yardley @timyardley]

Oracle to Make Gemini Models Available to Thousands of Enterprise Applications Customers https://t.co/GkQTGYR512

[Tim Yardley @timyardley]

Critical OpenWrt DHCPv6 Flaw Could Let Unauthenticated Attackers Run Code as Root https://t.co/FPZl73t7GG

[Tim Yardley @timyardley]

IonStack part II: GhostLock, a stack-UAF that has existed in ALL Linux distributions for 15 years | Nebula Security https://t.co/hGuSWbw7ZM

[Tim Yardley @timyardley]

Interesting read. https://t.co/O03nwx2Bja

[Tim Yardley @timyardley]

GitHub Copilot: Sorry Dave, I can't do that harmful thing - unless you ask me in code https://t.co/YpHRBBzimc

[Tim Yardley @timyardley]

30 papers · The reading list Ilya Sutskever gave John Carmack https://t.co/rOeiC55BZF

[Tim Yardley @timyardley]

Prompt Injection as Role Confusion https://t.co/guIJc9NMi4

[Tim Yardley @timyardley]

China-Linked Hackers Backdoored Linux Login Software to Hide for Nearly a Decade https://t.co/EcL9PO5CXi

[Tim Yardley @timyardley]

You can’t afford to lead agentic engineering from the sidelines https://t.co/UzX7elgJdb

[Tim Yardley @timyardley]

Cheap code means formal verification is reasonable now — Antfly Blog https://t.co/zVazuNI2v6

[Tim Yardley @timyardley]

DeepSeek-V4-Flash means LLM steering is interesting again https://t.co/hi3F33BvFU

[Tim Yardley @timyardley]

Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Lab https://t.co/9GCbanmEco

[Tim Yardley @timyardley]

Humanity faces an uncertain fate as experts brace for superintelligent AI https://t.co/bDJ7eEuHEP

[Tim Yardley @timyardley]

The AWS MCP Server is now generally available | AWS News Blog https://t.co/yxTAh1iOTF

[Tim Yardley @timyardley]

Behind the Scenes Hardening Firefox with Claude Mythos Preview - Mozilla Hacks - the Web developer blog -- https://t.co/FMhERAY21Q

[Tim Yardley @timyardley]

A tale of hope and positivity not despair -- Mozilla: Anthropic's Mythos found 271 security vulnerabilities in Firefox 150 - Ars Technica https://t.co/7UgH7axcA7

[Tim Yardley @timyardley]

MAD Bugs: Even "cat readme.txt" is not safe - Calif -- https://t.co/3Y3d47QrY5