Plss train abs ! Make your core stronger , not necessary to train abs to soo having ba strong core is more imp also i u are fat for god sake dont run just walk also gym karu jhat bhar gyaan chodu raat bhar
So i need to rent a gpu to learn inference now ! Waiting for exams to get end next week then , i will rent a gpu and slowly gonna build inference around a model ..
sameer_ retweeted
you can blame your college, gender, circumstances, youself all your college life, but the truth is if you really wanted to change something for the good, you would change what's needed. victim mentality will never take you any far.
Goated product achaa huaa wisper ka subscription nhi liyaa @Hiteshdotcom !
If you create a product, that is useful to you. In addition, all of your friends use it on regular basis.
It’s just a matter of time, it’s a hit product.
inApp.app is serving 150k links now
iType is another such product.
Also, I totally get it to compare iType with Wisper flow or many other open source version. But the architecture is fundamentally different.
You talk for 20s and it just dumps text, I wanted something real time.
Not to compete with anyone, just to have my own fun. And it’s free. I can afford to give a good few thousand users to have fun.
Finished building a voice-driven coding agent from scratch — base Claude SDK only, no LangChain, no Agent SDK wrapper.
Own loop. Own harness — approval gates, git-based rollback, denylist, checkpoint validation. Own skills system, loaded on demand. Voice as the final I/O layer on top.
~1000 unit tests plus a real benchmark suite against the live API.
repo:github.com/sameerjamliya-cmd…
sameer_ retweeted
TrenTorch.com is finally out.
The best way to learn Frontier ML for FREE
We cover things from
- Statistic for ML
- Classical ML
- Deep Learning
- Transformers & LLMS
- Distributed Training
- Reinforcement Learning
- Inference
ALL FOR FREEEEE
Feel free to check out the repo as well.
github.com/trentorch/trentor…
Amazing dev team
@Rocky_T07 @ShivtejG236 @aadityansha_06
Looking for sponsors
@vast_ai @modal @SarvamAI @hydra_db @googleaidevs @OpenAIDevs @OpenRouter @GroqLLC @ClaudeDevs @nebiusai @iitmadras @theo @ezSnippet @waitin4agi_ @kirat_tw @sheryians_ @ApnacollegeX @PhysicswallahAP
Everyone says learn inference, learn CUDA,learn ML
But almost nobody tells you exactly what to learn, how to learn it, or how to know whether you’ve actually learned it.
Introducing Trentorch.com a free, open-source platform to learn and practice Machine Learning, CUDA, and inference through hands-on coding.
Instead of just watching lectures or reading theory, you’ll:
• Learn the theory behind each concept
• Follow step-by-step implementation examples
• Solve coding challenges based on what you learned
• Implement algorithms from scratch, from foundational ML to Inference and CUDA kernel
• Practice problems in a Codeforces-style environment
• Get new Problem of the Day challenges with ratings
The goal isn't just to teach you how to write the code.
It’s to help you understand what your code is actually doing underneath.
We’re building Trentorch because advanced education shouldn’t be locked behind expensive subscriptions.
Money shouldn’t be the barrier to learning ML, inference, or CUDA.
A free alternative to platforms that charge students heavily every month.
signup and start solving problems now
Trentorch.com
wrote a 15M parameter gpt2 from scratch to understand what happens under the hood , learned so much from this . Thanks to @maanas_tyagi for recommending.
repo:github.com/sameerjamliya-cmd…
Learning difficult and complex things adds up Now, when I’m mentally exhausted, I find myself going back to things I used to struggle with and somehow, they’ve become my comfort zone. Maybe that’s what growth looks like.
learned pytorch by optimizing neural network from 80 to 95 percent accuracy ,also build CNN, RNN and next word predictor in way to learn !
repo:github.com/sameerjamliya-cmd…














