PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

The Data Wall, Agents, and Planning-Based Evals

josephthacker.com | blog | #ai-security | #llm | #agents | #training-data | #evals
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Joseph Thacker reflects on the LLM 'data wall' debate and outlines how planning-based evals could better assess agents.
Published
Collected

Related coverage

blog · portswigger.net
Enterprise Edition architecture
Burp Suite Enterprise Edition consists of a coordinating server, distributed scanning agents, a web server for the UI and REST API, and a database, scaling from a single machine to large agent pools.
blog · xbow.com
How Attackers Are Using AI & What Defenders Must Do
Attackers are running AI driven attack chains from recon to exploitation in minutes. Here’s what actually changed, and why defenders need AI pentesting to keep pace.
blog · projectblack.io
Bypassing EDR with Local AI
A pentest shows Claude refuses to build an LSASS dumper, but local DeepSeek and uncensored Qwen models produce a working XOR-encrypted minidumper, making AI-assisted EDR evasion nearly effortless.
blog · about.gitlab.com
What happens when vulnerabilities are discovered faster than you can fix them?
AI is changing how quickly vulnerabilities can be discovered and exploited. The next challenge is bringing that same speed to remediation and prevention
blog · hackerone.com
Measuring The Fix: How We Evaluate Frontier Models on Remediation Quality
HackerOne tested frontier models on security fix quality and found the judge mattered more than the model. See how CTEM remediation earns engineer trust.
blog · about.gitlab.com
Extend GitLab Duo Agent Platform into your business systems
Learn how to call a custom GitLab flow from Salesforce so every error arrives as a GitLab issue with root-cause analysis, ready to fix and deploy.
Back