News
AI, cybersecurity, machine learning, scraping & programming news.
Show HN: SeaSearch – Lightweight, S3-backed multi-tenant search engine
The search infrastructure most teams run today is Elasticsearch, and for good reason. It handles full-text search at scale, has a mature ecosystem, and its API has become the de facto standard. But Elasticsearch carries architectu...
Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs
A new research paper submitted to arXiv this week describes an attack method that undermines the core assumption behind large language model safety: that refusing harmful requests prevents harm. The technique, which the authors ca...
Agentic Societies Need a Social Harness
When AI Agents Talk to Each Other, They Need More Than a Protocol Imagine two AI agents, each working on behalf of a different person, trying to schedule a meeting. One has access to its principal's calendar. The other has access...
You Shall Not Pass into Ring-0! A User Privacy-Friendly Anti-Cheat Architecture for Personal Computers
Anti-Cheat Software Spies on Players. This Architecture Stops That. When you install a competitive game like Valorant or Fortnite, you also install kernel-level anti-cheat software. Riot Vanguard, Easy Anti-Cheat, BattlEye, and FA...
When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control
LLMs Should Know When to Say "I Don't Know" Language models are fluent by default. Ask them a question they cannot answer, and they will produce something that sounds right, reads well, and might be completely wrong. In healthcare...
Verifiable Social Reasoning for LLM Assistants
Why Your Chatbot Can't Read Between the Lines When you tell your LLM assistant that a coworker seems a little too eager to help, you're giving it a subjective, filtered, emotionally loaded account of reality. The assistant never s...
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
A Tabular Foundation Model That Learns Joint Distributions, Not Just Predictions Tabular data is the unglamorous backbone of machine learning in practice. Healthcare records, financial transactions, sensor readings, scientific mea...
JustFit: 200K-Token LLM Serving on a 24 GiB Laptop with Just-in-Time State Management
Fitting a 27B-Parameter LLM into 24 GiB of Laptop Memory The promise of local LLM inference is straightforward: run capable models on hardware you own, keep your data private, and avoid API costs. The obstacle is equally straightf...
World Model Science: Self-Organized Criticality, Weak Chaos, and Metastable Belief Dynamics in Long-Horizon LLM Agents
When an LLM agent runs a long task, it accumulates state: progress markers, beliefs, constraints, uncertainties, tool debt, and intermediate plans. Standard evaluation asks one question: did the final answer pass? This paper asks...
Knowledge as Orbit: Finite Collections as Phases of an Exactly Periodic Latent Generator
Machine learning stores knowledge extensionally. Every item in a collection gets its own code, its own latent vector, its own row in a codebook. For X objects, you need X entries. The question this paper asks is whether a finite c...