HackerNoon

How We Caught an LLM Scoring Bug and Fixed It Without Compromising Our Research

A 42-of-42 failure rate in our LLM benchmark was a parser bug. How we found it, fixed our scorer without fudging results, and ...

[Uncensored LLM Frontier #120] Distillation Delivery: How DoorDash Uses LLMs for Search and Personalization Without Direct Serving

DoorDash's contrarian proposal In this section, we cover the proposal by Raghav Saboo of DoorDash: "Distill LLMs for delivery, do not use them directly." While this claim may seem counterintuitive to ...

LLM x dbt MetricFlow: Building an 'Error-Free' Autonomous AI Data Agent That Eliminates Definition Drift

SQL' in Marketing Data Analysis and a New SolutionAre you tired of 'plausible but false SQL'?With the rise of generative AI, ...
Nature

‘Fighting fire with fire’ — using LLMs to combat LLM hallucinations

Karin Verspoor is in the School of Computing Technologies, RMIT University, Melbourne, Victoria 3000, Australia and in the School of Computing and Information Systems, University of Melbourne, ...
Ars Technica

Canadian legislator reads out apparent LLM response in floor speech

Anyone who has used the Internet in recent years is probably used to encountering telltale signs of LLM prompting that lazy users sometimes forget to remove from their AI-generated pabulum. But a ...