2024-10-30
LLM Security: Keep Untrusted Content in the User Role—Always 2024-07-11
AIs without levers are inert 2024-06-06
Improving LLM Alignment with Metric-Based Self-Reflection 2024-05-25
Intercepting LLM Streams for Improved Chat UX 2024-03-20
Tipping AI for better responses? 2024-03-02
Robots Talking To Machines 2023-12-13
Akihabara, and my reflections on the democratization of AI 2023-11-22
Multifaceted: the linguistic echo chambers of LLMs 2023-10-18
Simple LLM/GPT trick: “seeding” 2023-10-16
PSA: Always sanitize LLM user inputs 2023-10-15
Using History Insertion, Policy Drift and Allusions to jailbreak DALL·E 3 2023-09-29
Wanted: the engineer’s entrepreneur. 2023-09-14
Building Safe, Aligned & Informed AI Chatbots 2023-08-19
The silliness, lossiness, and bias of leetcode screening in tech 2023-07-28
Using LLMs to parse and understand proposed legislation 2021-03-09
Disability: Models, Cultures, Perceptions and the Path to Inclusivity.