ata VS blob

> My main gripe with it though is that the actual interface is quite limited, and I don't like having to navigate to the site every time I want to use it.

https://github.com/rikhuijzer/ata. Written in Rust. Does streaming responses and supports Emacs keyboard shortcuts. That's it. All that's needed for quickly looking up things.

- Checkout definitions. I have a small tool (https://github.com/rikhuijzer/ata) available on a keyboard shortcut and use it to quickly checkout definitions for words when I come across a word that I don't know.

As a little side-note, it actually involved some hacking to get the output printing correct because it appeared that the API sometimes responds denotes a newline by two tokens (["\", "n"]) and sometimes by one token (["\n"]). In the playground (https://platform.openai.com/playground), they convert the two token version to a single token, so that's what ata does too (details in https://github.com/rikhuijzer/ata/pull/6). My guess is that this is basically a bug in the model which they manually fixed in the Playground and ChatGPT front ends.

ChatGPT made my work more productive, but I was having a bit of a struggle with the browser, timeouts and slow responses, and the lack of keyboard shortcuts. That's why I made a terminal application: https://github.com/rikhuijzer/ata. You can download it for free in the releases section or build it yourself from source. I'm using it daily and hope it is useful for people here too

Actually, at Minsky Research Team (https://minsky.cc) we are working in a project called Blob (https://github.com/minskylab/blob), our motivation is change the way how we're define, develop and maintain software projects. This tool allows create a context representation of the source code and the files structure and use it to transform the project trough OpenAI GPT-3 API, from that, we can interact with source code in natural language.

Check out the project on GitHub at https://github.com/minskylab/blob.