Pouya Amiri
Hi there, welcome to my blog. I'm currently interested in mechanistic interpretability and alignment research. I run various ML experiments and record my findings here.
I'm also a Product Engineer at insightfactory.ai working across everything from infra to design, building a new platform for data analytics and AI.
I graduated from the University of Adelaide with a bachelor's in Computer Science (Advanced). During my studies I undertook research on the effectiveness of LLMs for ultrasound report generation. I also interned at the Australian Bureau of Statistics, Atlassian, and HENNGE (in Tokyo!).
I enjoy hiking. My favourite trail has been Sant Jeroni in Monserrat.
Things I'm learning / exploring (may or may not be up-to-date):
- Multi-agent RL
- Replacing attention heads with human-readable programs
- Improving monitorability through activation probes
If you're also excited about these topics, feel free to reach out!
Recent
-
Steering Language Models and Interpretability
A primer on how LLMs work and a recap of some of the experiments I've been doing on LLMs as I get into mechanistic interpretability.
-
Building a little robot
I had my love for robotics reignited recently, so I decided to build little robot.
-
Improving performance by understanding user behaviour
Improving the performance of an app usually happens by parallelizing tasks, writing faster code, or doing less work. But there is another way too, by leveraging user behaviour, to create the illusion of speed.
-
AX
AX. The overall experience of an AI Agent interacting with a product such as a website or app, especially in terms of how easy or token-efficient it is to use.