Fei Cheung

HongKonger, Maker, Teacher, Engineer. Interested in all sort of things, from physics to philosophy, hardware to software.

[Fei Cheung @FeiCheung1]

Drifting with an autonomous RC car using #JetsonNano.
Some people create ML model for race, I create ML model for memes.🤪
Check the details in my medium blog post: https://t.co/VKLdpLxm8w
@donkey_car #AutonomousVehicles #eurobeat #dejavu
#Drift #MEMES #AutonomousDrift

[Fei Cheung @FeiCheung1]

This is how I’m doing it. For critical functions/components/classes, I create test cases to ensure AI doesn’t break code in new generations. Using a TDD approach to manage risks while prompting new features.

[Andrej Karpathy @karpathy]

Noticing myself adopting a certain rhythm in AI-assisted coding (i.e. code I actually and professionally care about, contrast to vibe code).

1. Stuff everything relevant into context (this can take a while in big projects. If the project is small enough just stuff everything e.g. `files-to-prompt . -e ts -e tsx -e css -e md --cxml --ignore node_modules -o prompt.xml`)
2. Describe the next single, concrete incremental change we're trying to implement. Don't ask for code, ask for a few high-level approaches, pros/cons. There's almost always a few ways to do thing and the LLM's judgement is not always great. Optionally make concrete.
3. Pick one approach, ask for first draft code.
4. Review / learning phase: (Manually...) pull up all the API docs in a side browser of functions I haven't called before or I am less familiar with, ask for explanations, clarifications, changes, wind back and try a different approach.
6. Test.
7. Git commit.
Ask for suggestions on what we could implement next. Repeat.

Something like this feels more along the lines of the inner loop of AI-assisted development. The emphasis is on keeping a very tight leash on this new over-eager junior intern savant with encyclopedic knowledge of software, but who also bullshits you all the time, has an over-abundance of courage and shows little to no taste for good code. And emphasis on being slow, defensive, careful, paranoid, and on always taking the inline learning opportunity, not delegating. Many of these stages are clunky and manual and aren't made explicit or super well supported yet in existing tools. We're still very early and so much can still be done on the UI/UX of AI assisted coding.

[Fei Cheung @FeiCheung1]

Recently I got attracted by KAN, a promising alternative for MLP. I decided to write about my learning with KAN, Spline, and in a single blog post, and share my thoughts about it. TL;DR: MLP is a specific form of KAN

https://t.co/TbdVPqxIos
#KAN #AI #ML #NeuralNetworks

[Andrej Karpathy @karpathy]

GPT is a new kind of computer architecture that runs on text. Yes it can talk to us, but also to much of our existing software infrastructure. First via apps on top of APIs, now inside ChatGPT via plugins.
What a time right now...
https://t.co/HjeUCv3XE7

[Andrej Karpathy @karpathy]

I was asked about what AI will look like in 3 decades. Reminder: it has not even been 1 decade yet since the ImageNet moment (though the anniversary is very close, imo October 13, 2022 per https://t.co/NPg2sm2Ojm). Imagining that much change, but 3X, and on an exponential is 🤯

[Fei Cheung @FeiCheung1]

Is this something we can teach in school?

[Lex Fridman @lexfridman]

Human tendency to conform, especially when in large groups, is terrifying. Propaganda machines leverage this throughout human history.

The way out is to think freely, detached from the divisive narratives of the day that masquerade as universal truths.

This often feels lonely.

[Fei Cheung @FeiCheung1]

AlphaFold: Using AI for scientific discovery | DeepMind https://t.co/70rqjsFg2u

[Fei Cheung @FeiCheung1]

@armand_dpl @nvidia Are you using model based or model free algo?

[Fei Cheung @FeiCheung1]

I was interested in the derivation of Neural ODE and spent some time to go through the details and proof. Some friends suggest me to write a blog post about and why not!
#MachineLearning #NeuralODE #NeuralNetworks
https://t.co/pGoeeMwHdw

[Fei Cheung @FeiCheung1]

@donkey_car @marcoleewow @flyyufelix

[Fei Cheung @FeiCheung1]

Drifting with an autonomous RC car using #JetsonNano.
Some people create ML model for race, I create ML model for memes.🤪
Check the details in my medium blog post: https://t.co/VKLdpLxm8w
@donkey_car #AutonomousVehicles #eurobeat #dejavu
#Drift #MEMES #AutonomousDrift

[Fei Cheung @FeiCheung1]

@fermatslibrary 1. Changing Magnetic field induced Electric field (eq3
2. Changing Electric field induced Magnetic field (eq4

Literally nothing:

Nothing: OSCILLATE!

[Fei Cheung @FeiCheung1]

@chenqiushi404 把名子都搵成繁體字？

[Fei Cheung @FeiCheung1]

A great teacher

[Grant Sanderson @3blue1brown]

Polar plots of primes. Wait for it...

Can you guess what's going on? See the new video: https://t.co/zY12KNNt1r

[Fei Cheung @FeiCheung1]

I wonder if pi4 can achieve the same thing...

[Fei Cheung @FeiCheung1]

Wow

[でべ @devemin]

Jetson Nanoで、Unity3DとUnityちゃんを動かす神が現れたようです。みなさんの声とニーズがあれば続報があるかもしれないとのこと・・・？！

これはぜひ拡散しましょう！♪

[Fei Cheung @FeiCheung1]

Learn a lot from @flyyufelix and @marcoleewow. We exchange a lot of idea and try making #DonkeyCar work better under different condition! #jetsonNano #maker #autonomousvehicle

[Felix Yu @flyyufelix]

A detailed account on the methods we tried to tackle overfitting and improve robustness for Donkey Car at Pixmoving Hackathon
https://t.co/dz72Fgcth2

@FeiCheung1 @marcoleewow @diyrobocars @thepixmoving #DonkeyCar

[Fei Cheung @FeiCheung1]

@marcoleewow @flyyufelix We had tried a lot of new things on @donkey_car including using the new #JetsonNano. By setting the framerate to 60hz, the result is already better than Rpi model! We tried diff stuff including CV, ML model and hardware. Stay tuned for the details!

[Fei Cheung @FeiCheung1]

@Ingmar_Stapel Are you installing keras with apt-get / pip? Your sd card will need to be larger than 32gb and there are small variation across different brand. I suggest installing the package manually.

[Fei Cheung @FeiCheung1]

@JasonBenner7 @diyrobocars @feicheung Yes sure ! I am doing it now. I didn’t use it for training (you know, leftover projects😂) but my friend @flyyufelix do try it on the pi.

[Fei Cheung @FeiCheung1]

Jetson Nano is out and I can’t wait to try it on #donkeycar . I write a tutorial on how to set up the #donkeycar with #JetsonNano and hope it will save you some time! https://t.co/GFMQ4aXJRw #embedded #machinelearning #maker #autonomousCar #donke