daniel__hami Profile Banner
Daniel Hami Profile
Daniel Hami

@daniel__hami

Followers
136
Following
773
Media
116
Statuses
802

The relationship between humans and technology has always been a question of balance. Technology only becomes truly valuable when it serves human values.

Slovak Republic
Joined December 2017
Don't wanna be here? Send us removal request.
@daniel__hami
Daniel Hami
1 month
Built a mini CRM in Python that auto-replies to Gmail inquiries, extracts names/phones/emails with AI, and logs everything to Google Sheets. No Zapier. No manual copy-paste. Just pure automation magic. What do you think of it ? Github link is below 👇
4
0
8
@daniel__hami
Daniel Hami
17 days
Want to cut your LLM input costs by 50% and speed up responses? Use prompt caching (prefix caching) it stores the model’s internal work for the start of your prompt and reuses it when the next request begins with the same tokens. This can: Slash latency by up to 80% Cut
0
0
1
@csaba_kissi
Csaba Kissi
20 days
6 Open Source Projects For Web Developers
21
49
373
@daniel__hami
Daniel Hami
22 days
Hood morning gang 😎
3
0
3
@daniel__hami
Daniel Hami
23 days
What is a parameter in LLMs? Parameters are the key numbers inside the model that it learns during training to make predictions. They include weights and biases. (If you see, for instance, “20B” after an LLM’s name "gpt-oss:20b ", it means the model has approximately 20 billion
0
0
1
@daniel__hami
Daniel Hami
23 days
Good morning guys 🌞🌞
4
0
6
@daniel__hami
Daniel Hami
24 days
What are transformers and why are they so popular? Transformers are a kind of neural network architecture that became the standard building block for modern LLMs like GPT, Claude, and Gemini. They are designed to handle sequences (like text) very efficiently and with strong
0
0
1
@daniel__hami
Daniel Hami
24 days
Good morning guys! Have a great Sunday 🌞
4
0
2
@daniel__hami
Daniel Hami
25 days
Which one do you use and for what purpose? Base Models: Foundational models that predict the next sequence of text based on input. They are used in a structured manner for Q&A interactions. Chat Models: These evolved from base models and use reinforcement learning from human
1
0
4
@daniel__hami
Daniel Hami
26 days
Good morning guys! 🌞
6
0
7
@daniel__hami
Daniel Hami
27 days
In this video, you’ll see how to install Ollama and browse the available models to find the ones that fit you best. https://t.co/PoIVn63vdb
@daniel__hami
Daniel Hami
29 days
Day 1 What is Ollama and how to use it ? Ollama is a free, open-source tool that allows users to run, manage, and customize large language models (LLMs) locally on their own computer
0
0
0
@daniel__hami
Daniel Hami
27 days
Did you know you can run small language models locally for free using just an API call? In this short video I’ll show you how to get started. In my previous video I walked you through installing Ollama, and now we’ll build on that to make your first local AI request from code.
3
0
4
@daniel__hami
Daniel Hami
29 days
Day 1 What is Ollama and how to use it ? Ollama is a free, open-source tool that allows users to run, manage, and customize large language models (LLMs) locally on their own computer
1
0
3
@daniel__hami
Daniel Hami
1 month
Just morning guys ! ✨
0
0
2
@daniel__hami
Daniel Hami
1 month
Hood morning everyone ! Let’s start the week 💪
4
0
4
@daniel__hami
Daniel Hami
1 month
Good morming everyone ! I’ve just come through a substantial week. Finally, the weekend is here. Enjoy it ;)
2
0
2
@csaba_kissi
Csaba Kissi
1 month
You can read 100 tutorials. But real coding begins when your code doesn’t work and you start to debug it yourself.
53
6
163
@daniel__hami
Daniel Hami
1 month
It turned out which language is the most effective for communication with AI. A recent study by the University of Maryland and Microsoft tested 26 languages on major AI models like OpenAI, Google Gemini, and Llama, finding that Polish outperforms English (ranked 6th) with 88%
1
0
2
@daniel__hami
Daniel Hami
1 month
In Silicon Valley, 99% of startup companies have their code written by AI, and the remaining 1% are breaking down from debugging. What do you think about is ?
5
0
2
@daniel__hami
Daniel Hami
1 month
The layers of AI are good for certain problems. For the layers and also the activation functions, it’s true that if you come up with one that works and performs better for a given problem than all the others. Does that mean you’ve just changed the world?
2
1
2
@daniel__hami
Daniel Hami
1 month
Good morning everyone ☀️☕️
5
0
5