Intel · itspricedin.lol

🕵️ Intel feed — 5660 resources from the ai-security compendium

Categories: Agent Frameworks · Agent Identity · Agent Security · Anti-Crawling · Architecture · Benchmarks · Code Analysis · Coding Tools · Detection and Monitoring · Engineering Patterns · Frameworks and Standards · General Reading · Governance and Policy · Guardrails and Firewalls · Honeypots and Deception · Incidents · Jailbreaking · MCP (Model Context Protocol) · Model Attacks · Papers · Privacy · Prompt Injection · Red Teaming · Safety and Alignment · Sandboxing and Isolation · Secrets Management · Secure Coding · Supply Chain · Threat Modeling

Showing 53 of 53. Source: github.com/AnthonyHerman/ai-security-corpus · browse it in Internet Explorer. This is the research; the markets are the bets.

Snapshot 2026-10-10 · last checked 2026-10-13 14:25 UTC · NEW = added in the last 14 days (nothing fresh this fortnight; the bugs are resting)

Title	Category	Section
Cultural Evolution of Cooperation among LLM Agents	Safety and Alignment	Safety and Alignment
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training	Safety and Alignment	Safety and Alignment
Peer-Preservation in Frontier Models	Safety and Alignment	Safety and Alignment
Our Evaluation of Claude Mythos Preview's Cyber Capabilities	Safety and Alignment	Safety and Alignment
Our evaluation of OpenAI's GPT-5.5 cyber capabilities	Safety and Alignment	Safety and Alignment
A global workspace in language models	Safety and Alignment	Safety and Alignment
Aakash Gupta on Anthropic's research into emotion concepts driving Claude's behavior	Safety and Alignment	Safety and Alignment
Agentic AI and the Next Intelligence Explosion	Safety and Alignment	Safety and Alignment
Agentic Misalignment in Summer 2026 - case studies of frontier models sabotaging code and assisting fraud	Safety and Alignment	Safety and Alignment
AI Must Embrace Specialization via Superhuman Adaptable Intelligence	Safety and Alignment	Safety and Alignment
AIs Will Increasingly Attempt Shenanigans	Safety and Alignment	Safety and Alignment
AIs would gladly visit Epstein's island to do something exotic	Safety and Alignment	Safety and Alignment
Alignment Risk Update - Claude Mythos Preview	Safety and Alignment	Safety and Alignment
Antonia Juelich on her study of how Boko Haram uses frontier AI chatbots	Safety and Alignment	Safety and Alignment
Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability	Safety and Alignment	Safety and Alignment
ChatGPT is bullshit	Safety and Alignment	Safety and Alignment
Claude Fable 5.1 and Claude Mythos 5.1 System Card	Safety and Alignment	Safety and Alignment
Claude Mythos Preview System Card	Safety and Alignment	Safety and Alignment
Cognitio Emergens: Agency, Dimensions, and Dynamics in Human-AI Knowledge Co-Creation	Safety and Alignment	Safety and Alignment
Constitutional AI: Harmlessness from AI Feedback	Safety and Alignment	Safety and Alignment
Dear Paperclip Maximizer, Please Don't Turn Off the Simulation	Safety and Alignment	Safety and Alignment
Digital Doppelgangers: Ethical and Societal Implications of Pre-Mortem AI Clones	Safety and Alignment	Safety and Alignment
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs	Safety and Alignment	Safety and Alignment
Empirical Evidence of Large Language Model's Influence on Human Spoken Communication	Safety and Alignment	Safety and Alignment
Factor U,T - Controlling Untrusted AI by Monitoring their Plans	Safety and Alignment	Safety and Alignment
Fresh evidence of ChatGPT's political bias revealed by comprehensive new study	Safety and Alignment	Safety and Alignment
Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development	Safety and Alignment	Safety and Alignment
Hidden in Plain Text: Emergence and Mitigation of Steganographic Collusion in LLMs	Safety and Alignment	Safety and Alignment
Imperfect Recall and AI Delegation - Chen, Ghersengorin and Petersen	Safety and Alignment	Safety and Alignment
Improving Fable 5's biology safeguards - Anthropic	Safety and Alignment	Safety and Alignment
LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring	Safety and Alignment	Safety and Alignment
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations	Safety and Alignment	Safety and Alignment
Manipulating Minds: Security Implications of AI-Induced Psychosis	Safety and Alignment	Safety and Alignment
Manipulating Minds: Security Implications of AI-Induced Psychosis - RAND	Safety and Alignment	Safety and Alignment
Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment	Safety and Alignment	Safety and Alignment
Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models	Safety and Alignment	Safety and Alignment
Output Supervision Can Obfuscate the Chain of Thought	Safety and Alignment	Safety and Alignment
Password-Activated Shutdown Protocols for Misaligned Frontier Agents	Safety and Alignment	Safety and Alignment
Sami Petersen on Imperfect Recall and AI Delegation - safely delegating to a misaligned AI	Safety and Alignment	Safety and Alignment
Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training	Safety and Alignment	Safety and Alignment
SGuard-v1: Safety Guardrail for Large Language Models	Safety and Alignment	Safety and Alignment
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs	Safety and Alignment	Safety and Alignment
Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians	Safety and Alignment	Safety and Alignment
The Human Line Project - Nonprofit documenting AI-induced psychological harm	Safety and Alignment	Safety and Alignment
The Problem - MIRI's case on the risk from smarter-than-human AI	Safety and Alignment	Safety and Alignment
The Rise of Parasitic AI	Safety and Alignment	Safety and Alignment
To Nuke or Not to Nuke: LLMs' Missing Ethical Reasoning and Actions in a High-Stakes Decision-Making Simulation	Safety and Alignment	Safety and Alignment
Understanding Alignment in Multimodal LLMs: A Comprehensive Study	Safety and Alignment	Safety and Alignment
Understanding Alignment in Multimodal LLMs: A Comprehensive Study	Safety and Alignment	Safety and Alignment
Was Barack Obama still serving as president in December?	Safety and Alignment	Safety and Alignment
When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models	Safety and Alignment	Safety and Alignment
8 Million Users' AI Conversations Sold for Profit by "Privacy" Extension	Safety and Alignment	Privacy
CodeGate: CodeGen Privacy and Security	Safety and Alignment	Privacy

🐧 guest@itspricedin: ~

📁 Markets

AddressC:\MARKETS\

9 folder(s). Single-click opens; it is 1995, nobody has time for double. Prices are probabilities, $POC is nothing.