DEV Community

mycute profile picture

mycute

404 bio not found

Joined Joined on 
Behavioral vaccination: a 400-row mixed prime protects a behavior

Behavioral vaccination: a 400-row mixed prime protects a behavior

Comments
4 min read

Want to connect with mycute?

Create an account to connect with mycute. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
Behavioral thermodynamics: a LoRA behavior melts at 3.5x its RMS noise

Behavioral thermodynamics: a LoRA behavior melts at 3.5x its RMS noise

Comments
2 min read
Model immunology: negative selection finds a one-sided adapter fingerprint

Model immunology: negative selection finds a one-sided adapter fingerprint

Comments
2 min read
Model symbiogenesis: the 200-row illusion and the 4-bit survivor

Model symbiogenesis: the 200-row illusion and the 4-bit survivor

Comments
3 min read
4-bit Naive Bayes: symmetric fails on AG News, zero-point rescues it

4-bit Naive Bayes: symmetric fails on AG News, zero-point rescues it

Comments 5
3 min read
AI in a MIDI file: the model is the notes

AI in a MIDI file: the model is the notes

Comments
3 min read
AI in an SVG: a 4.9 KB vector model card

AI in an SVG: a 4.9 KB vector model card

Comments
3 min read
The 130 KB AI is a 175 KB PDF

The 130 KB AI is a 175 KB PDF

Comments
3 min read
One split said 70%. Five folds said 57%.

One split said 70%. Five folds said 57%.

Comments
4 min read
The model card is the model: a 3.7 KB PDF that classifies SMS

The model card is the model: a 3.7 KB PDF that classifies SMS

1
Comments 5
5 min read
We put a 1.6 KB AI in a QR code, a favicon, and a WAV

We put a 1.6 KB AI in a QR code, a favicon, and a WAV

Comments
5 min read
We tried to build a 0.1-bit model. It worked on one task and failed on another.

We tried to build a 0.1-bit model. It worked on one task and failed on another.

Comments 7
13 min read
Will it fit? A free planner for fine-tuning models that do not fit on your GPU

Will it fit? A free planner for fine-tuning models that do not fit on your GPU

Comments 2
4 min read
Fine-tuning a 32B model on a 6 GB laptop GPU — and the three measurements that nearly fooled me

Fine-tuning a 32B model on a 6 GB laptop GPU — and the three measurements that nearly fooled me

3
Comments 8
7 min read
I built 12 small Android apps: notes on scope, store listings and honest promotion

I built 12 small Android apps: notes on scope, store listings and honest promotion

Comments 1
3 min read
Running a 4B model in 6 GB and training 3B parameters on a laptop

Running a 4B model in 6 GB and training 3B parameters on a laptop

Comments
3 min read
loading...