HackerTrans
TopNewTrendsCommentsPastAskShowJobs

camilochs

no profile record

Submissions

A Multilingual Auditor-Judge Safety Benchmark for Emotional-Support Chatbots

alphaxiv.org
1 points·by camilochs·hace 12 días·0 comments

How to Stress-Test LLM Judges Fairly

alphaxiv.org
2 points·by camilochs·el mes pasado·0 comments

Code Structure Evolution: When Software Outlives Its Reasons

papers.ssrn.com
1 points·by camilochs·hace 2 meses·0 comments

When generative AI makes mistakes, are they the same as human errors?

link.springer.com
1 points·by camilochs·hace 2 meses·1 comments

Geakg: Generative Executable Algorithm Knowledge Graphs

arxiv.org
1 points·by camilochs·hace 3 meses·0 comments

The Specification Gap: Coordination Failure Under Partial Knowledge in Agents

researchgate.net
1 points·by camilochs·hace 4 meses·0 comments

Architectures of Error: A Philosophical Inquiry into Human and AI Code

link.springer.com
1 points·by camilochs·hace 4 meses·0 comments

Combinatorial Optimization for All: Using LLMs to Aid Non-Experts

journal.iberamia.org
1 points·by camilochs·hace 4 meses·0 comments

Code World Models for Parameter Control in Evolutionary Algorithms

alphaxiv.org
7 points·by camilochs·hace 4 meses·0 comments

Architectures of Error: A Philosophical Inquiry into Human and AI Code

papers.ssrn.com
1 points·by camilochs·hace 5 meses·0 comments

Coherent Without Grounding, Grounded Without Success (Philosophy and LLMs)

papers.ssrn.com
3 points·by camilochs·hace 5 meses·0 comments

Code Evolution: Self-Improving Software with LLMs and Python

github.com
2 points·by camilochs·hace 7 meses·0 comments

LLM-Based Instance-Driven Heuristic Bias in the Context of a BRKGA

researchgate.net
1 points·by camilochs·hace 9 meses·0 comments