Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models

Related Stories

How large are large language models?

Large language models are improving exponentially?

Can Large Language Models Play Text Games Well? (2023)

Researchers Found a Better Way to Teach Large Language Models New Skills

Small language models are the future of agentic AI

OLMo 2 - a family of fully-open language models

The Dangers of Stochastic Parrots: Can Language Models Be Too Big?

ESIM Security

Apple Intelligence Foundation Language Models Tech Report 2025

Prefered way to structure polars expressions in large project?

Evaluating the Effectiveness of Memory Safety Sanitizers

Apple Intelligence Foundation Language Models Tech Report 2025 [pdf]

Turkey bans xAI's Grok over offensive content

Easy dynamic dispatch using GLIBC Hardware Capabilities

Evaluating the factuality of verifiable claims in long-form text generation

A human metaphor for evaluating AI capability

Evaluating publicly available LLMs on IMO 2025

Russia Blocks Ethical Hacking Legislation Over Security Concerns

Upcoming coordinated security fix for all Matrix server implementations

Jack Dorsey Says His 'Secure' New Bitchat App Has Not Been Tested For Security

Firefox Security & Privacy newsletter 2025 Q2

AccountingBench: Evaluating LLMs on real long-horizon business tasks

Not sovereign: Microsoft cannot guarantee the security of EU data

Leveraging Elixir's hot code loading capabilities to modularize a monolithic app

Large-scale DNA study maps 37,000 years of human disease history

Jurisdiction Is Nearly Irrelevant to the Security of Encrypted Messaging Apps

Formal Security and Functional Verification of Cryptographic Protocol Implementations in Rust

MakeShift: Security Analysis of Shimano Di2 Wireless Gear Shifting in Bicycles

Hugging Face Is Hosting 5,000 Nonconsensual AI Models of Real People

Structuring large Clojure codebases with Biff