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

Internal Monologue Capture

josephthacker.com | blog | #ai-security | #llm | #expertise | #hacking | #prompting | #fine-tuning
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Joseph Thacker proposes 'internal monologue capture': experts record their real-time thought processes, giving AI apps tacit expertise—like an XSS pro's reasoning—via prompts or fine-tuning.
Published
Collected

Related coverage

blog · josephthacker.com
Hacking with ChatGPT: Ideal Tasks and Use-Cases
Joseph Thacker shares when ChatGPT shines for hacking tasks — medium-size jobs with no existing tool — plus use-cases like writing data-processing scripts and de-minifying JavaScript for bug hunting.
blog · josephthacker.com
Yes. LLMs can create convincingly human output.
Joseph Thacker explains why RLHF makes LLMs default to a formal academic tone, and shares prompting strategies—informal requests, vocabulary limits, style examples—for human-like output.
blog · bishopfox.com
Capture the Flag to Advance Your Hacking Skills
Three Bishop Fox consultants explain how capture-the-flag competitions build practical skills in exploitation, cryptography, reverse engineering, and forensics, and help advance security careers.
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
Back