Researcher
Riley Goodside
Current role not listed
Goodside helped turn prompt engineering into an applied discipline at Scale AI and later worked at Google DeepMind. His public experiments exposed how untrusted text can override model instructions, helping bring broad attention to prompt injection as a security problem for LLM applications.[1]
Career & education
Google DeepMind2025-2026
Scale AI2022-2025Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
References
- Prompt injection attacks against GPT-3simonwillison.net
Simon Willison documents Goodside’s early demonstration of how text given to GPT-3 could override the instructions in a translation prompt.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed July 15, 2026 · Checked for accuracy and new information.