16 results for "domain use"
Don't use localhost:3000, use your own custom domain
After presenting a demo of how an internal tool works, I was flooded with questions. Not about the tool, but about why I had bought a domain just to run the demo. "Why didn't you use the staging serve…
moved to a new domain, added some tools, and created a category i didn't expect to need
tolop.space got a few updates this week. new domain first, was on a vercel subdomain before, moved to .space because the whole idea of the site is finding tools in a new space. felt like the right fit…
Domain-Filtered Knowledge Graphs from Sparse Autoencoder Features
Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and we…
GoDaddy gave a domain to a stranger without any documentation
What would you do if your organization had used a domain name for 27 years, and the registrar holding the domain seized it without any advance warning? All…
Why are top university websites serving porn? It comes down to shoddy housekeeping.
Hundreds of subdomains from dozens of universities have been hijacked by scammers.…
LLMs Corrupt Your Documents When You Delegate
Large Language Models (LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation t…
How Reform Happens
What determines whether and how regulations are reformed? We use a newly constructed data set of 3,590 successful and failed regulatory reforms in 189 countries, between 2005 and 2022, to address this…
An Intelligent Fault Diagnosis Method for General Aviation Aircraft Based on Multi-Fidelity Digital Twin and FMEA Knowledge Enhancement
Fault diagnosis of general aviation aircraft faces challenges including scarce real fault data, diverse fault types, and weak fault signatures. This paper proposes an intelligent fault diagnosis frame…
Tandem: Riding Together with Large and Small Language Models for Efficient Reasoning
Recent advancements in large language models (LLMs) have catalyzed the rise of reasoning-intensive inference paradigms, where models perform explicit step-by-step reasoning before generating final ans…
Information-Theoretic Measures in AI: A Practical Decision Guide
Information-theoretic (IT) measures are ubiquitous in artificial intelligence: entropy drives decision-tree splits and uncertainty quantification, cross-entropy is the default classification loss, mut…
QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems
We explore a central question in AI for mathematics: can AI systems produce original, nontrivial proofs for open research problems? Despite strong benchmark performance, producing genuinely novel proo…
Explanation Quality Assessment as Ranking with Listwise Rewards
We reformulate explanation quality assessment as a ranking problem rather than a generation problem. Instead of optimizing models to produce a single "best" explanation token-by-token, we train reward…
Adaptive ToR: Complexity-Aware Tree-Based Retrieval for Pareto-Optimal Multi-Intent NLU
Multi-intent natural language understanding requires retrieval systems that simultaneously achieve high accuracy and computational efficiency, yet existing approaches apply either uniform single-step …
PhysNote: Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model
Vision-Language Models (VLMs) have demonstrated strong performance on textbook-style physics problems, yet they frequently fail when confronted with dynamic real-world scenarios that require temporal …
NeSyCat: A Monad-Based Categorical Semantics of the Neurosymbolic ULLER Framework
ULLER (Unified Language for LEarning and Reasoning) offers a unified first-order logic (FOL) syntax, enabling its knowledge bases to be used directly across a wide range of neurosymbolic systems. The …
The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications
Given the increased use of LLMs in financial systems today, it becomes important to evaluate the safety and robustness of such systems. One failure mode that LLMs frequently display in general domain …