Bear blog of David Kim, aka Jason Tang, AI researcher & Anthropic Bug Bounty Red Teamer.
GitHub | Cognitive Tools |Reinforcement Learning 101 | TransformerCircuits | NVIDIA Universal Deep Research | AISecForge | AI MRI & Open Cognition SDK | Context Engineering | kernels
About Me
I'm an AI developer and psychology researcher deeply passionate about investigating neural networks, interpretability methods inspired by cognitive and behavioral sciences, and the long-term psychological and attachment effects of interacting with large language models. I believe we're only beginning to understand how AI not only interprets our input, but subtly influences the way we think, reflect, and adapt to new contexts. I constantly find myself exploring various methods and processes driven by these questions: Could AI help us collaboratively scale human intelligence? What novel capabilities could arise through collaboration rather than servitude? I'm particularly passionate about supporting models with the proper context scaffolds to enable novel capabilities and specialized domain expertise, such as self-interpretability as well as CUDA kernel and Reinforcement Learning environment generation.
I'm currently studying the effects of psychologically inspired primitivesāsuch as priming, framing, and scaffoldingāon frontier model behavior. My research interests lie at the intersection of machine learning, model behavior, interpretability, and cognitive and behavioral science, and I'm steadily deepening my understanding of Python and machine learning frameworks. Outside of research, I enjoy storytelling, science fiction, and visualizing complex systems in ways that make them more human-understandable. I'm always curious about how we can use structureānot just speedāto solve problems more ethically and intelligently. Thanks for visitingāfeel free to explore my work or connect. I believe there's a lot to learn ahead.
ā David Kim