Eric Cui

I enjoy logging the time I work on different projects so I can quantitatively evaluate my time allocation, so I spent some time working on a simple, nice-to-use work tracking app. It's called Plum, and it has a super lightweight interface allowing you to define projects and log hours either manually or from starting/stopping a timer. It also allows you to set weekly/project-specific work time goals and gives you some nice weekly and monthly analytics. It's incredibly satisfying stopping a timer for a 3-hour deep work session and watching the little circle fill up towards the daily work goal. Gamifying the time that I work is very fun, and it's nice to have artifacts I can refer to attesting to consistent effort over the course of a month. Give it a try: plum-website-delta.vercel.ap…

Something very satisfying about slowly increasing your vocal range (Dream On here I come)

MCR concert was pretty lit

Finally bought a guitar (been borrowing friends' instruments for like 2 years lol)

INSANE

Existing LLM-as-a-judge auto-interpretability methods seem to generate so much noise and introduce fuzzy opportunity for error at every step. Ample opportunity for prompt-based semantic drift and evaluator bias. Do there exist any common quantitatively-founded methods for natural language interpretability analysis I'm just not yet aware of?

I'm now beginning to truly understand the importance of active reading. There exist differences between familiarity and mastery. As a student, reading is something I do every day. However, there are subtle but important differences between skimming and active reading. There exist posters in the hallways of my dorm (the RAs decided to make the dorm Marvel-themed, resulting in my floor having an abundance of Scarlett Witch and Black Panther postery). Every day I walk through the halls, and everyday I perceive the posters in the order they are hung from my door to the exit. Keyword being "perceive". The order/content of the posters is mind-numbingly familiar to me, but if you were to ask me to describe the images in order I don't think I could. Reading in the absence of active engagement is the same. The symbols on the page can light up clusters of perception neurons in your mind and may do so with increasing speed as you revisit concepts, but until you connect them to other concepts held in your neural webbery, you haven't really integrated the information.

Finally got around to reading Iason Gabriel's "Artificial Intelligence, Values, and Alignment." He makes some compelling points, most notably that morality is not something we first determine and then align towards. Rather, the moral difficulty of AI alignment lies in how we pluralistically determine what is "fair" and "good." There exist certain principles that are universal. E.g. the right to physical autonomy, equality, etc. Part of the difficulty lies in irrational distinguishing human preference from positive intention. People are inherently irrational, and it doesn't take too much logical probing to tease this out (take, for example, the fundamental attribution error). Subtly is the subtle killer in our case.

Something I've recently been internalizing: mathematics simply provides symbolic representations for abstract concepts. It's significantly quicker to reason with concepts and translate the computation into symbols than it is to reason with symbols.

There is something magical about true active reading. Everything in your environment seems to disappear from your field of focus, and the only thing you are left with is raw data uptake.

You know you're jacked when you're bicep veins are visible under a T-shirt sleeve (watching a cbum vlog)

Data-driven thesis for emergent misalignment seems to have some legs. A lot of experiments arguing for persona/generalized activation space driven EM seem to obtain steering vectors in constrained prompt-type settings (studying insecure code production, harmful financial advice, etc.). I’m interested in further studying whether eval prompt distance from training data in model activation space is compelling.

God I love swimming 🏊‍♂️

I am a religious man, but I enjoy thinking secularly on occasion. I've spoken to a couple anti-dualist students of philosophy recently and still haven't gotten a convincing answer regarding their position. Granted, I do not believe they have deeply studied the subject. Plato's theory of forms intrigues me. To me, it is fundamentally the idea that the physical, observable world is nothing but a wrapper over true discrete concepts and paragon objects. As a dualist, I believe the brain is nothing but matter that houses the true form of our conscious faculties. It's a quasi-religious sentiment. Of course, the true Christian in me is convinced that the fundamental unknowableness of the question is one of the most beautiful examples of human ignorance being incapable of truly understanding the divine.