James PadolseySimple LLM/GPT trick: “seeding”How to coerce a response with less up-front promptingOct 18, 20232Oct 18, 20232
James PadolseyPSA: Always sanitize LLM user inputsProtect yourself from different types of attacks that can expose data or functionality that you’d rather keep private.Oct 16, 2023Oct 16, 2023
James PadolseyUsing History Insertion, Policy Drift and Allusions to jailbreak DALL·E 3A quick attempt to contravene content policies with ‘history insertion’ and ‘policy drift’ to create images of political figures.Oct 15, 20232Oct 15, 20232
James PadolseyBuilding Safe, Aligned & Informed AI ChatbotsAn analysis and walkthrough of how to build a safe, capable and truly aligned AI chatbot with ChatGPTSep 14, 20232Sep 14, 20232
James PadolseyThe silliness, lossiness, and bias of leetcode screening in techAt some point in the last ten years, LeetCode-like interview/screening platforms re-invaded tech and beautifully inserted themselves as the…Aug 19, 2023Aug 19, 2023
James PadolseyUsing LLMs to parse and understand proposed legislationLegislation is famously challenging to read and understand. Indeed, such documents are not even intended to be read by the average person…Jul 28, 2023Jul 28, 2023
James PadolseyDisability: Models, Cultures, Perceptions and the Path to Inclusivity.And how we can move towards a more accessible and inclusive society for all.Mar 9, 20211Mar 9, 20211
