Dr Mark Greenaway

I did my PhD in computational statistics, with @john_t_ormerod on variational approximations. I'm a Data Scientist @ CBA.

[Dr Mark Greenaway @certifiedwaif]

@AkiretaHK @MurrayJones22 Maybe R for Political Science Research.

[John D. Cook @JohnDCook]

OpenAI says it’s impossible to create useful AI models without copyrighted material.

That's their defense?!

"Your honor, it would be impossible for me to do what I want to do without breaking laws, so it must be OK."

[Anthony Bonato @Anthony_Bonato]

I feel very attacked.

[Yann LeCun @ylecun]

Funny how some folks who think theory has some magical properties readily dismiss bona fide engineering and empirical science as alchemy.

Blind trust in theoretical results that turned out to be irrelevant is a major reason why neural nets were dismissed between 1995 and 2010.

[Modular @Modular]

Mojo🔥 is now available for download locally to your machine! ❤️‍🔥🚀 

Beyond a compiler, the Mojo SDK includes a full set of developer and IDE tools 🛠 that make it easy to build and iterate on Mojo applications. Let’s build the future together!🔥

https://t.co/KxmLvsxx5e

[Patrick Blumenthal @PatrickJBlum]

from left to right:
- tensor tony: got his name from smuggling A100s into NY and NJ ports. if you need compute, TT's your man, (just don't ask where they came from)
- Kev: singlehandedly responsible for using trading algos to pump Gamestop in 2021. charged with 5 counts but lawyers did they thing
- shkreli: yallready know
- wookie: muscle of the crew but don't let that fool you, homie caused a blackout at MDC using nothing but a raspberry pi
- snoop: the pytorch purist, don't even mention tensorflow around this dude less you wanna catch a CUDA core to the dome
- bubbles: did a nickel up in sing sing, just got out. bro barely touched fresh air and he's already got a cluster running in the projects paid for by NYC energy grants

yall heard nothing tho

[Richard McElreath 🐈‍⬛ @rlmcelreath]

I told a colleague that logistic regression is AI and they got mad at me, so I made a chart. Find yourself. I am "Tinder is AI".

[Dr Mark Greenaway @certifiedwaif]

@PhDemetri Know how you feel. I feel incredibly isolated as well.

[Dr Mark Greenaway @certifiedwaif]

@ajordannafa I used to use <- in R just so I could see at a glance which language I was programming in.

[Tom Carpenter, PhD (@tcarpenter.bsky.social) @tcarpenter216]

“Shitpostering”

[𝕐𝕖𝕞𝕖𝕖𝕟 @yemeen]

My favorite part of Oppenheimer was the mathematician telling them not everything can be linearly approximated and then they fired him

[Sean Baxter @seanbax]

I have my first working C++ NLL borrow checker tests.

Use the ^ (shared) and ^^ (mut) borrow types. The "no mutable aliasing" rule is enforced at compile time.

The birth of Memory Safe C++!

[Jacob Jameson 📊 @JacobCJameson]

Some of you missed the most shocking part of the EJMR paper. It was this as.factor(year) legend in figure 9

[Dr Mark Greenaway @certifiedwaif]

@PhDemetri My Casio fx-100AU with S-VPAM (Super Visually Perfect Algebra Mode) could own that thing. 60 AUD at OfficeWorks.

[Alvin Christian @_AlvinChristian]

About to do some machine learning. Wish me luck.

[Dr Mark Greenaway @certifiedwaif]

@tcarpenter216 Switching languages constantly is mind-bending. And zero-based indexing versus one-based indexing is yet another thing to worry about ...

[Charlie Marsh @charliermarsh]

There's an extremely interesting conversation going on in Python right now around the future of performance.

It's centered on @colesbury's PEP 703, which makes the GIL optional (to be removed entirely in the future), but comes at a cost.

Here's my summary...

[Karl Rohe @karlrohe]

Daily statistics reminder:

you are assuming independence somewhere. It’s a very powerful assumption and I doubt statistics as a field could exist without it. However, that assumption is likely far more concerning than any choice of marginal distribution (eg Gaussian)