Viewing profile — graphitout

For a chatbot like claude code, since the instruction prompt part (including descriptions of tools) is relatively constant for multiple users and over a long time, a lot of optimiz…

We are not there yet. A bit too optimistic for today. May be in 1 year. I added types to a python codebase (50k) using claude code and it still took some effort to make mypy happy.…

Very nice. Just the thing I was looking for.

Yes. Most of the MCP based search lookup now happens over the text stage. voicevoyage.io looks interesting. Will keep an eye.

Quite funny to see that coming from OpenAI. Nevertheless, how can they prove that?

What is the strategy to deal with pay-as-you-go services used in vibe coded apps? I am always worried about the risk of some bad loop consuming thousands of dollars in a day.

Very interesting. The moment I saw the repo I looked for a python reference implementation and found: https://github.com/antirez/voxtral.c/blob/main/python_simple... Thanks a lot! …

Claude gave me $50 yesterday with the release of opus4.6 and I burned my session quota + $30 yesterday itself. The code changes were very reasonable. It is good for handling all co…

The RAG was setup on a bunch of documents, most of them were manuals containing steps about measurements, troubleshooting, and replacing components of industrial machines. The issu…

I do not follow. Could you clarify please? Who is going to fund and what is the criteria they are using?

optimal chunk size is strongly query-dependent - very true. Faced similar issues. Ended up adding a agentic tool call layer on the top to retrieve the nearby chunks to handle a cas…

Nice visualization. Would be nice to also see state variables (like stack or queue) along with the graph.

Vilberta is a speech-to-speech/text chatbot using a pipeline that combines voice acivity detector (VAD), speech recognition (ASR), a large language model (LLM), tool calling (via M…

I wanted to test vibecoding in a less familiar territory. I have never worked with ReactJS and have limited experience with TypeScript. Therefore, trying out a small frontend-only …

You are right. - llm_generate() - this is the core function which calls ollama API - get_related() - this will give a sequence of related topics for a given topic and description -…

Very interesting. Eight healthy subjects used for testing. I am guessing that the effect is not limited to humans alone. Shouldn't it be easier to do a larger study on animals?

Lately, I've been tinkering with llama.cpp and the ollama server. The speed of these tools caught my attention, even on my modest 4060 setup. I was quite impressed with the generat…

Is there an example NNET to see how it is used?

First focus on inference. It is a lot costlier to have GPUs for inference.

Additive synthesis was a pain to configure. I had to model and estimate the behavior of each harmonic. It was too much effort. Subtractive synthesis didn't work that well for me ei…

You are right. I needed that image to explain the parameters in the ADSR configuration I used in the project. Mainly the slevel1 and slevel2 which captures the slow decay during su…

Sure. Audio files generated have no license. Do whatever with it. Only the code has license, but I have no intention to enforce it. I am playing gooberdash now.

I had some fun with the strings in the karplus-stress-tester. Thank you for that link. I am thinking of moving the core to WASM. But I may have to drop the python part and make the…

This is part of my journey on pybind11. I wrote a tiny FM Synthesis library in C++ and a Python wrapper for that using pybind11. There is a command-line piano app in the examples d…

I like the tool. Is there a way to make the app move to the middle. Currently all the content appears on the left side.