I saw this on code night someone was claiming it would give a free Claude API and it actually worked.

Verify with telegram and it not gonna cause u anything it just send /start command to bot that's all .

https://freemodel.dev/invite/FRE-ec9dd58d
It's give u free Claude api access which u can use with Claude cli just signup and verify with telegram and get ur 10$ Claude api credit.

Got the free 3-day trial of the new Super Grok coding agent and this thing is absolutely cooking my project rn .

https://freemodel.dev/invite/FRE-ec9dd58d
It's give u free Claude api access which u can use with Claude cli just signup and verify with telegram and get ur 10$ Claude api credit.

To the 8 ppl who just signed up but forgot to verify via Telegram please go back to the site and complete the verification so we can both get the $10 credit!

ahhh this is literally taking forever

For my ml project, I started with two ideas:

- A baldness/makeup classifier 
- An Ethiopian music genre classifier 

Both ran into the same problem: data.

Finding a quality dataset for the makeup project was nearly impossible, and since i don't know enough about music manually labeling Ethiopian music genres would have taken forever.

after of getting stuck I pivoted.

I used a movie API to collect data, downloaded hundreds of movie posters, and built an movie image genre classifier that predicts movie genres from poster images alone.

The training process was full of trial and error:

- 📉 Epoch 1: High validation loss — the model was underfitting. 
  🔧 Fix: Standardized image dimensions and preprocessing across the dataset so the model could learn meaningful patterns.

- 📈 Epoch 10: Validation performance started dropping — classic overfitting. The model was memorizing posters instead of generalizing.

- ✅ Epoch 3: The sweet spot. Balanced training and validation loss with solid performance metrics.

One thing this project taught me:

> Machine Learning isn't just about writing code. It's about collecting data, cleaning it, experimenting with models, tuning hyperparameters, analyzing results, and repeating the process until everything clicks.

The model isn't always the hardest part. Sometimes the real challenge is the data itself.

Lesson 2 was all about deploying a model to production exporting the final .pkl file after training and finally deploying it on Hugging Face unfortunately I had a hard time doing that because I encountered errors from gradio on the huggingface when passing image data to the model so I left that part for now and just ran it in Google Colab instead I tested it there and it was quite interesting.

Do it or do not do it either way you will regret both.

Soren Kierkegaard