<![CDATA[Testing LLM and sharing my personal experience with them]]> https://rss.com/podcasts/testing-llm-and-sharing-my-personal-experience-with-them So here I try to play around with LLMs either in my projects or in HuggingFace and share what I think about them. Testing can range from using them to code, develop software, ask dumb questions, summarize a text, etc.

]]> RSS.com 2026.907.134739 Fri, 11 Sep 2026 12:02:03 GMT en 1263bccd-7dbd-5f3d-9fb0-aa2761b6d23e https://media.rss.com/testing-llm-and-sharing-my-personal-experience-with-them/podcast_cover_20260906_233952_c62c54074284f803ddc224564c12b6b1.jpg Testing LLM and sharing my personal experience with them https://rss.com/podcasts/testing-llm-and-sharing-my-personal-experience-with-them no Mohammad Jawad Barati Mohammad Jawad Barati Mohammad Jawad Barati false episodic podcast Bremen, Free Hanseatic City of Bremen, Germany false <![CDATA[Will OpenRouter be always OpenAI-Compatible API?]]> Short answer, no.

But it is OpenAI compatible for the most part or at least what I have seen. BTW if you are curious about my experiment you can look at this Jupyter Notebook: https://github.com/kasir-barati/smart-novel-beatrice/blob/bcb520b3ca73531eb93c650004090865b9f0f7db/local-setup/notebooks/openrouter_qwen_tts_voices.ipynb

I love JN for testing and experimenting LLMs. Let me know your goto tool when testing and checking what is possible.

]]> https://rss.com/podcasts/testing-llm-and-sharing-my-personal-experience-with-them/3140400 e6e50e10-6e78-4d67-8871-03f36e47dbe4 347 full 3 3 Thu, 10 Sep 2026 17:48:02 GMT false false <![CDATA[Qwen3 14B vs. GPT-4o Mini]]> In this episode I compared and talked about these two models. Which one is faster, which one is cheaper and which one I decided to use.

And this is the JupyterNotebook I talked about it in this episode: https://github.com/kasir-barati/smart-novel-beatrice/blob/3ee5d89d91f94e4f4903ede1d2009350f040f4fb/local-setup/notebookes/tts_sanitiation.ipynb

This is the link in question for comparing the two models on OpenRouter: https://openrouter.ai/compare/qwen/qwen3-14b/openai/gpt-4o-mini

]]> https://rss.com/podcasts/testing-llm-and-sharing-my-personal-experience-with-them/3135458 ceb509b0-f7b9-4f2e-abf7-48d374496a75 596 full 2 2 Tue, 08 Sep 2026 21:18:23 GMT false false <![CDATA[Qwen3-TTS vs. Gemini-TTS]]> I was in the middle of experimenting with LLMs to generate audio files for my smart-novel app (although at the moment the LLM-powered part lives in https://github.com/kasir-barati/smart-novel-beatrice). That is why I decided on testing Qwen3-TTS and Gemeni-TTS. Let me know what you think?

BTW this is the text I gave both LLMs: [dramatic] The system chimed:

And this is the style instruction I gave Qwen3-TTS (note that Gemini-TTS does not accept such a thing): A male narrator with clear and easy to understand voice. Treat things like [dramatic], [proud], etc as emotion tags. But make sure to not mistake them for other text which are not emotion tags. Also you should not read < or > in a text, just pause a few milliseconds before reading them.

]]> https://rss.com/podcasts/testing-llm-and-sharing-my-personal-experience-with-them/3129551 e05c964a-dc11-43aa-82a4-d2e8ef16c1c0 399 full 1 1 Mon, 07 Sep 2026 00:03:46 GMT false false Bremen, Free Hanseatic City of Bremen, Germany