Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications. However, as LLMs have improved, so have the attacks against them. Prompt injection attack is listed as the #1 threat by OWASP to LLM-integrated applications, where an LLM input contains a trusted prompt (instruction) and an untrusted data. The…

In order to produce effective targeted therapies for cancer, scientists need to isolate the genetic and phenotypic characteristics of cancer cells, both within and across different tumors, because those differences impact how tumors respond to treatment. Part of this work requires a deep understanding of the RNA or protein molecules…

A few months ago, I learned this the hard way: never rely on a cheap DRAM-less SATA SSD in a heavily used system, especially one handling constant OS updates and virtual machines. Despite having an NVMe drive in my rig, I overestimated the durability of that cheap SATA SSD and…