Cody (@codez) header
Cody (@codez) profile picture

Cody

@codez

Developer. Researcher. AI/ML. Computer Vision. Python. C++.

 ldn/blr
Joined August 2020
  • Tweets910
  • Following396
  • Followers1.3K
Vibe coding
Image from Cody (@codez)
1
1
39
I got 128 GB of RAM sticks and I'm using them to play Tetris. Please somebody tell Sam Altman.
Image from Cody (@codez)
Pubity (@pubity) profile picturePubity
@pubityOct 30
OpenAI CEO Sam Altman believes people owning RAM is wasteful, and that it belongs in data centers instead. "From a global allocation perspective, actually, it’s quite terrible to have everyone have a bunch of the world’s limited supply of DRAM sitting in their own computer."
Image from Pubity (@pubity)
Image from Pubity (@pubity)
59
Why is the Anthropic Claude logo like a virus?
Image from Cody (@codez)
39
Found this in my ChatGPT history. It's been a couple of years.
Image from Cody (@codez)
40
When you get your ironed shirt back, but it was folded.
Image from Cody (@codez)
1
32
The new MacBook pro touch. You can touch it from any angle. Wow! Innovation.
Image from Cody (@codez)
48
Hey, @X algorithm! I'm looking to #connect with people interested in: - Tech - Programming - AI/ML - App Development - SaaS & Product Building - Open-Source I write about machine learning and tech. Hit me up if you wanna be friends with me. 🥹👉🏻👈🏻
Image from Cody (@codez)
20
1
15
312
"You are not in the list of sudoers. This incident will be reported." #Linux
Image from Cody (@codez)
2
74
Triplet loss is a way to train models so that similar things end up close together and different things end up far apart. You feed the model three examples at a time: - an anchor (the reference) - a positive (something that should be similar to the anchor) - a negative (something that should be different) The loss pushes the anchor and positive closer in the embedding space while pushing the anchor and negative farther apart, usually by at least some margin. It’s commonly used in: - face recognition - image retrieval - recommendation systems - any task where you care about similarity rather than exact class labels The basic idea is simple: don’t just learn to classify. Learn a space where distance means something useful.
Image from Cody (@codez)
41
Linkedin you sicko
Image from Cody (@codez)
35
Load more