Jaskaran Singh (@jasksing) header
Jaskaran Singh (@jasksing) profile picture

Humanity is Awesome! | Engineer

Joined June 2021
Photo by Jaskaran Singh (@jasksing)Photo by Jaskaran Singh (@jasksing)Photo by Jaskaran Singh (@jasksing)Photo by Jaskaran Singh (@jasksing)Photo by Jaskaran Singh (@jasksing)Photo by Jaskaran Singh (@jasksing)Photo by Jaskaran Singh (@jasksing)Photo by Jaskaran Singh (@jasksing)Photo by Jaskaran Singh (@jasksing)Photo by Jaskaran Singh (@jasksing)
Replying to @cneuralnetwork
Resnet Unet Inception net
2
2,278
Jaskaran Singh retweeted
How does Photokeeper achieve near instant image classification even on edge devices? The trick is we are not using one single large image model, instead we are using a 5-step pipeline with each step scoring a single aspect of the image A thread 🧵
My phone gallery is almost 60% screenshots, memes and random forwards from whatsapp. So I built an app that scans your photos and finds them for you (to delete)! Introducing Photokeeper: extremely lightweight on device photo organizer tool. Fully open source. Runs on anything. <10 ms per photo. 2.6 MB model. Runs fully offline, nothing leaves your device.
1
1
3
60
Jaskaran Singh retweeted
My phone gallery is almost 60% screenshots, memes and random forwards from whatsapp. So I built an app that scans your photos and finds them for you (to delete)! Introducing Photokeeper: extremely lightweight on device photo organizer tool. Fully open source. Runs on anything. <10 ms per photo. 2.6 MB model. Runs fully offline, nothing leaves your device.
3
1
1
6
409
Replying to @sabeer
To know that you are free to create your own meaning and happy to pursue it.
1
1
165
Jaskaran Singh retweeted
I hate to admit it, but this was my literal reaction. (NSFW: Language)
208
1,894
234
38,457
2,101,782
Jaskaran Singh retweeted
Replying to @AlfredoABrown
Imagine you're there watching the Wright Brothers get in their flying machine back in the early 1900s, and being like "in what scenario is this necessary?" You're telling on yourself.
64
68
2
2,704
38,510
Jaskaran Singh retweeted
Arnab finally met someone he couldn't mute. 😂 Anmol walked into his studio and demanded proof for the 'Pakistan-backed CJP' claims. Arnab kept shouting, while the BJP spokesperson looked completely lost. All that noise, not one straight answer.
180
2,238
52
12,673
1,378,124
Restaurants are dead. Chefs are dead. I just bought an airfryer and I can cook anything. And recipes are on the internet for free!!
236
702
139
8,800
234,906
Replying to @Gauri_the_great
Autoresearch on inference engineering?
1
40
Regularized learning will be next ! -JEPA
Encoder-decoder → classification → contrastive learning. We’re so back in the 2020s. 😂 Maybe the next-token-prediction LLM tsunami made us forget that some older ideas were actually really good.
2
107
Replying to @miniapeur
More layers
33
Replying to @paraschopra
Because taste changes with time. Time series forecasting?
2
400
The autoregressive nature makes it sure.
another bitter lesson: there are no emergent properties. it’s all in the data
1
143
Jaskaran Singh retweeted
What is the purpose of higher education in the age of AI? I had a very candid conversation with my students about pedagogy, universities, and what needs to change. Sharing it here to hear what others think. The link for the full talk is in the first reply.
251
852
159
4,686
711,065
this is a bit different from what anthropic employees are posting on AI killing humans, but when I saw videos from the chinese humanoid games this year, I was terrified eventually the armed forces of any country will soon have to face those humanoids equipped with aligned/unaligned superintelligence just look at the rate of improvement, its only going to get better from here
4
3
66
3,096
Replying to @atulit_gaur
Humans : 2 AI : -1
7
In order to learn anything from scratch - you need to know how the universe was invented. Start from abstraction and let your curiosity take the front seat.
respectfully fuck this list. you don't need to "master" virtual memory before you write your first kernel. you need to write a broken kernel, watch it segfault, and go find out why. that's where you actually learn what a page table is. checklists like this are how people stay "preparing" for two years and never ship a single line of CUDA i stopped following advice like this. now i just start: naive kernel, profile it, get humbled, fix one thing, repeat. every os/systems concept on this list i actually understand, i learned by hitting it mid-optimization, not by reading it in a vacuum first. go write the broken kernel!!
1
5
63
3,365
Replying to @atulit_gaur
Maths, Experimenting and Constraints
3
611