Prompt Engineering

Applied to Using ideologically-charged language to get gpt-3.5-turbo to disobey it's system prompt: a demo by Milan Weibel 4mo ago

Applied to Please Understand by Sam Healy 8mo ago

Applied to LLM keys - A Proposal of a Solution to Prompt Injection Attacks by Peter Hroššo 1y ago

Applied to Extrapolating from Five Words by Gordon Seidoh Worley 1y ago

Applied to The Stochastic Parrot Hypothesis is debatable for the last generation of LLMs by Quentin Feuillade--Montixi 1y ago

Applied to Chess as a case study in hidden capabilities in ChatGPT by Tobias D. 1y ago

Applied to MetaAI: less is less for alignment. by Cleo Nardo 1y ago

Applied to Tutor-GPT & Pedagogical Reasoning by Courtland Leer 2y ago

Applied to $300 for the best sci-fi prompt by RomanS 2y ago

Applied to DELBERTing as an Adversarial Strategy by Matthew_Opitz 2y ago

Applied to Readability is mostly a waste of characters by Vlad Gheorghe 2y ago

Applied to LW is probably not the place for "I asked this LLM (x) and here's what it said!", but where is? by lillybaeum 2y ago

Applied to You can use GPT-4 to create prompt injections against GPT-4 by WitchBOT 2y ago

Applied to Hutter-Prize for Prompts by rokosbasilisk 2y ago

Applied to Remarks 1–18 on GPT (compressed) by Cleo Nardo 2y ago

Applied to Are nested jailbreaks inevitable? by Andrew Judson 2y ago

Applied to Want to predict/explain/control the output of GPT-4? Then learn about the world, not about transformers. by Cleo Nardo 2y ago

Applied to The Waluigi Effect (mega-post) by Cleo Nardo 2y ago