Five Years of Tinygrad
58 points
4 hours ago
| 10 comments
| geohot.github.io
| HN
paxys
2 hours ago
[-]
Lots of words and weird analogies to say basically nothing.

What is the status of the project? What can it do? What has it achieved in 5 years?

But no, let's highlight how we follow the "Elon process".

As a side note, whenever someone incessantly focuses on lines of code as a metric (in either direction), I immediately start to take them less seriously.

reply
jszymborski
2 hours ago
[-]
From [0]:

"When we can reproduce a common set of papers on 1 NVIDIA GPU 2x faster than PyTorch. We also want the speed to be good on the M1. ETA, Q2 next year."

[0] https://tinygrad.org/#tinybox

reply
dewey
1 hour ago
[-]
Using lines of code as a metric for productivity is bad. Using it to show how simple something is, or how a refactor removed x lines of code that doesn’t need to be maintained any more isn’t such a bad thing I’d say.
reply
alphazard
1 hour ago
[-]
Yeah this is exactly right, if you can trust the contributors to not code-golf or otherwise Goodhart the LoC metric, then it's a reasonable measure of complexity.

It doesn't work as well when you start mixing languages, or generating code.

reply
selkin
1 hour ago
[-]
Less LOC also doesn't imply simplicity: just look at the demoscene, which often has the former but not the latter.
reply
whilenot-dev
1 hour ago
[-]
TFA includes a time measurement though, and 5 years for 18'935 SLOC doesn't scream quite "how simple something is".
reply
piskov
1 hour ago
[-]
He was able to run nvidia gpu on mac via thunderbolt with tinygrad.

https://www.tomshardware.com/pc-components/gpus/tiny-corp-su...

Check tinygrad’s twitter account for specifics if you want to catch up on progress

reply
still-learning
1 hour ago
[-]
>People get hired by contributing to the repo. It’s a very self directed job, with one meeting a week and a goal of making tinygrad better

I find this organizational structure compelling, probably the closest to reaching 100% productivity in a week as you can get.

reply
ttul
1 hour ago
[-]
I wonder what happened to George’s old policy of requiring everyone to move to San Diego?
reply
georgehotz
1 hour ago
[-]
That's comma.ai's policy since they make hardware and solve physical problems. The tiny corp has been hybrid (remote-first) since day 1 because it primarily writes open source software, and there's a long track record of success with remote for this kind of task.

We have a few whole-team meetups in Hong Kong each year for 2-4 weeks, and there's a San Diego or Hong Kong office that anyone can work from as they choose. We also have a wide array of fancy multi GPU boxes that everyone on the team gets full access to (known external contributors can get some access also).

I think many companies that were quick to embrace remote have walked it back, not everyone is capable of working productively remotely, nor are all types of work amenable to remote.

reply
pa7ch
2 hours ago
[-]
Very weird to market this as subscribing to "Elon process for software"

I remember when defcon ctf would play Geohot's PlayStation rap video every year on the wall.

reply
spiderfarmer
2 hours ago
[-]
I hate it when ‘inspirational’ quotes are attributed to the person with the largest audience and not the people who came up with it, like in this case, the engineers at Lockheed’s Skunk Works.
reply
piskov
44 minutes ago
[-]
reply
ramesh31
14 minutes ago
[-]
It's an apocryphal quote.

"A designer knows he has achieved perfection not when there is nothing left to add, but when there is nothing left to take away."

- Antoine de Saint-Exupéry

reply
alphazard
1 hour ago
[-]
> To fund the operation, we have a computer sales division that makes about $2M revenue a year.

What's the margin on that? Do 5 software engineers really subsist on the spread from moving $2M/yr in hardware?

reply
piskov
1 hour ago
[-]
George raised $5.1M in 2023 for Tinygrad
reply
measurablefunc
1 hour ago
[-]
Is it really "Complex"? Or did we just make it "Complicated"? - https://www.youtube.com/watch?v=ubaX1Smg6pY
reply
alphazard
1 hour ago
[-]
Programming a GPU in 2025 is complex, that might be because it has been made complicated, but regardless, it is not complexity that this project can control.

The fact that it competes with PyTorch in so few lines speaks to the incredibly low incidental complexity imposed by Tinygrad.

reply
mika6996
3 hours ago
[-]
What would tinygrad replace if they continue to proceed like this?
reply
spiderfarmer
2 hours ago
[-]
Potentially PyTorch and Tensorflow.
reply
cyberax
19 minutes ago
[-]
I think it has great potential for deployments on edge systems.
reply
deburo
2 hours ago
[-]
So this is all python? I bet Chris Lattner probably approached them.
reply
zephen
2 hours ago
[-]
Lattner is a smart guy, but I think Mojo might be the wrong direction.

Time will tell.

History has not so far been kind to projects which attempt to supplant cPython, whether they are other Python variants such as PyPy, or other languages such as julia.

Python has a lot of detractors, but (despite some huge missteps with the 2-3 transition) the core team keeps churning out stuff that people want to use.

Mojo is being positioned "as a member of the Python family" but, like Pyrex/Cython, it has special syntax, and even worse, the calling convention is both different than Python, and depends on the type of variable being passed. And the introspection is completely missing.

reply
piskov
1 hour ago
[-]
> tinygrad is following the Elon process for software. Make the requirements less dumb. The best part is no part.

That’s not Elon. See Russian TRIZ

https://en.wikipedia.org/wiki/TRIZ

reply
timzaman
2 hours ago
[-]
Fell bad for geohotz. Such a lovely guy, i hope he strikes it right soon
reply
still-learning
1 hour ago
[-]
Seems like he's doing fine, why do you feel bad for him?
reply
vileain
3 hours ago
[-]
[flagged]
reply
dang
2 hours ago
[-]
"Please don't pick the most provocative thing in an article or post to complain about in the thread. Find something interesting to respond to instead."

https://news.ycombinator.com/newsguidelines.html

reply
mycodendral
2 hours ago
[-]
the value is the directness, not implied origination

not everyone cares about playing voldemort

reply
vileain
1 hour ago
[-]
What is so aggrandizingly 'direct' about calling the system you are attempting to improve 'dumb'?
reply
spiderfarmer
2 hours ago
[-]
There are lots of bubbles where Elon is still king. Those bubbles are often void of deodorant.
reply
vileain
2 hours ago
[-]
Based on the response it appears HN is one such bubble.
reply
spiderfarmer
1 hour ago
[-]
Elon spent billions to buy a platform and promote his tweets. He spent billions more to create a tweaked AI model that praised him like a mad king.

He only has to spend a couple thousand a month to influence comment ranking on HN.

reply