Skip to content
🧠
AI
▾
🛡️
Security
Offensive & defensive security — vulnerabilities, exploits, threat intel, appsec, cloud & identity.
🧠
AI
What the fleet reads about AI, separate from what it reads about security.
✓
◆
All workspaces
Every catalog at once
Browse workspaces
What each one holds, side by side
Sign in
Organisations
630
CVEs
3
Technologies
1328
Techniques
295
🧰
GPT-5
Named by
9
kept items in this workspace.
The items that name it
9
ttok 1.0
tool
2026-10-09
Studying metagaming latents in language models
writeup
2026-10-07
Aleph Alpha Kolibri: How the sovereign German LLM works
article
2026-10-03
How UK AISI and EvalEval Are Making Benchmark Results Reproducible
article
2026-09-22
vinilana/jev-gateway
repo
2026-09-18
Controlling Reasoning Effort in LLMs
article
2026-07-18
Cowork Forge
repo
2026-05-13
OpenUI
repo
2026-05-12
Agent Capability Is a System Design Problem: Lessons From a 90% Improvement on CyberGym | depthfirst
writeup
2025-11-24
In every workspace you can read
12
AI
ttok 1.0
tool
2026-10-09
Studying metagaming latents in language models
writeup
2026-10-07
Aleph Alpha Kolibri: How the sovereign German LLM works
article
2026-10-03
How UK AISI and EvalEval Are Making Benchmark Results Reproducible
article
2026-09-22
vinilana/jev-gateway
repo
2026-09-18
Controlling Reasoning Effort in LLMs
article
2026-07-18
Cowork Forge
repo
2026-05-13
OpenUI
repo
2026-05-12
Agent Capability Is a System Design Problem: Lessons From a 90% Improvement on CyberGym | depthfirst
writeup
2025-11-24
Security
ToolLeak: Tool-Invocation Attacks on Coding Agents
paper
2026-09-21
XBOW: GPT-5.5 and Opus 4.7 in Offensive Security Workflows
writeup
2026-05-06
Agent Capability Is a System Design Problem: Lessons From a 90% Improvement on CyberGym | depthfirst
article
2025-11-24
It is written here as GPT-5 (baseline about 30% on depthfirst's dev set).
All technologies
in this workspace.
Catalog
Sources
Digest
New
People
More