Here’s a running list of tiny workflow tips that make my day-to-day noticeably smoother. Most of these are embarrassingly simple, but that’s the point! Habits that seem obvious to me might be totally new to someone else (and vice versa). I’ll keep updating this as I discover more. Many are specific to Mac + Chrome. Feel free to message me your favorites and I’ll include them! Cmd+l to get to search bar Cmd+1, Cmd+2, ... to navigate between tabs Cmd+ ` to get around windows of the same...| Vincent Cheng
What I’m Doing Now (updated 4/19) Working on an AI control project with Josh Clymer Thinking about and trying to make good evals Deciding what to do over the summer School| Vincent Cheng
Hey! I’m Vincent Cheng, an freshman Math-CS major at UCSD. I’ve attended Ross, WARP, IOAI, and was an 2023 Atlas fellow. I change my mind about things very often, but wanting to learn new things is a constant! I’m interested in math, ML, what the future with AI will look like, Brazilian Jiu-Jitsu, arm-wrestling, and meeting new people. Message/email me! I read a lot of articles and save them in my Curius bookshelf! Check it out and get Curius yourself too.| Vincent Cheng
This web app uses your webcam, a lightweight depth model, and three.js to recreate that oddly satisfying metal pin toy effect. Try it out here Check out the code here.| Vincent Cheng
What do truly long-context models look like? I want to give the model all my journals, notes, pictures, previous work, etc. so that it can make connections and tailor responses for me. I imagine this to be In-between context stuffing and fine-tuning. Every ~day, the model takes all the conversations from that day and decides which to use to update its weights. In the future, will everyone have custom models? Predictive processing? What will human-AI collaboration look like in the future? How ...| Vincent Cheng
Some ideas I find interesting but don’t have enough time to make a reality. A “See all context” button. This is especially useful for reasoning models since I want to know which parts of the reasoning were dropped so I know how much context to provide. You would have to drop sensitive information like like system prompts. JARVIS. Models are capable enough already! We just need some better scaffolding like Cursor and some way to fit in a lot of context. I really liked GPT with scheduled ...| Vincent Cheng
The Man In The Arena It is not the critic who counts; not the man who points out how the strong man stumbles, or where the doer of deeds could have done them better. The credit belongs to the man who is actually in the arena, whose face is marred by dust and sweat and blood; who strives valiantly; who errs, who comes short again and again, because there is no effort without error and shortcoming; but who does actually strive to do the deeds; who knows great enthusiasms, the great devotions; w...| Vincent Cheng
Brazilian Jiu-Jitsu (BJJ) is a grappling sport which means there is no punching or kicking and you win by gaining dominant positions or submissions such as chokeholds or joint locks. What Makes BJJ Different? BJJ is the “broadest” sport I’ve done. It feels like math in the sense that you have so many distinct, but related, concepts to learn and problem-solving to do. In tennis or basketball, I felt like after building up the basics, I was repetitively honing small details to eek out 1-3...| Vincent Cheng
obviously non-exhaustive Monster (Japanese movie): messes with your head. 8/10 Squid Game The Prestige: It’s so good. I don’t get how it’s not Interstellar-level popular. 10/10 Alice in Borderland Top Gun Money Heist Stranger Things Arrival 火神的眼淚 模仿犯 Open (Agassi biography) Three Body Problem series When Breath Becomes Air Tomorrow, and Tomorrow, and Tomorrow How Not to Be Wrong Norwegian Wood There is No Antimemetics Division| Vincent Cheng
My opinion of whether Cursor helps or hinders my work has fluctuated significantly over the past few months. Cursor is really powerful. Having never worked with selenium drivers and barely editing any lines of code, I made a pretty nice scraper in two afternoons. It just works. However, there’s a pretty significant distinction of using AI code editors that I haven’t seen explicitly stated anywhere. The first way is tabbing to autocomplete code I’ve written hundreds of times, giving me m...| Vincent Cheng
I thought this video was really fun and wrote up some of the derivations that the video went over quickly. Introduction and Basic Principles Maupertuis’ principle of least action states that the action, defined as: $$ S_0 = \sum mvs $$ where $m$ is the mass, $v$ is the velocity, and $s$ is the distance, reaches a minimum along the actual path of motion. Euler later generalized this to a continuous form:| Vincent Cheng
Some weird stuff happens in high-dimensions. Reference 1. High Dimensional Oranges Are Almost All Peel Consider an $n$-dimensional cube of side length 1 containing a smaller $n$-dimensional cube with side length $0.8$ (“pulp”) surrounded by a $0.1$-width border (“peel”). The volume of the pulp is $0.8^n$, which rapidly approaches 0 as $n$ increases: DimensionsPulp Volume ($0.8^n$) 10.800 20.640 30.512 50.328 100.107 200.012 500.000014 Another perspective: To randomly sample a point in...| Vincent Cheng
Many people have written about curating a very goodTwitterfeed, but I have yet to see anyone talk about doing this with Youtube. I don’t know if many people do it but don’t talk about it, don’t do it, or what. I guess “subscribe to tons of accounts you enjoy, use the “Not Interested” for ones you want to avoid, and harvest” is not very deep. YouTube’s algorithm is very good at recommending content you would enjoy and I’ve more consciously used that to curate my YouTube feed ...| Vincent Cheng
Noam Shazeer and Jeff Dean on Dwarkesh arithmetic very cheap. moving data around is expensive. model parameters are very memory efficient: one fact per parameter? (this probably isn’t the right way to think about it because of superposition?) versus in context, there are kqv which can many more bits inference improvement thing? big model verifier, small model does it first thing?? “drafter models”. are these real? i don’t see how these parallelize. oh wait no you can batch it so it go...| Vincent Cheng
I want this to be an informal/public notebook where I record thoughts that are too long for a non-premium Twitter account, notes on different things I’m reading, and maybe more formal writings as well. The target audience for this page is a mix of myself and current/potential friends. Through this notebook, I hope to “produce” more and write better. For the longest time, I’ve been thinking my consuming to producing ratio has been higher than I would like, and hence I’m forcing mysel...| Vincent Cheng
Here are some ways I use LLMs that I think are making me dumber: When I want to build a Chrome extension for personal use, instead of actually learning and writing the JavaScript, I Claude-Code the whole thing in a couple of hours without writing a single line of code. Instead of taking the usual route which would leave me with more actual familiarity with JavaScript, I now shortcut the process, leaving me with barely any JS knowledge despite numerous functioning applications. When I need mat...| Vincent Cheng