Richard Abrich

To begin with, instead of the full timetracking task, let's just simplify to much simpler spreadsheet tasks, e.g. "enter the value 'foo' into cell C3".

https://huggingface.co/papers/2407.09025 > SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

There are two pieces: 1. whenever a replay happens, record as much as possible about the replay action automatically (e.g. date/time, strategy, strategy arguments) 2. As a developer, I would...

ChatGPT: --- To automatically instrument the execution of `replay.py` and ensure that all relevant inferences are stored to the database efficiently and systematically, you can utilize Python's decorators and context...

ChatGPT: --- To handle the replay ID automatically and ensure it's used seamlessly throughout the execution of `python -m openadapt.replay` without the developer needing to set it manually, you can...

Let's also implement basic functionality for displaying in the dashboard.

@KrishPatel13 I think for this to be considered completed we will need to implement automated tests which evaluate each provider on a dataset we curate. This is low priority for...

Once we start scaling we should consider supporting B2, e.g. app.py: ``` """Lambda-like function for generating a presigned URL for uploading a recording to B2.""" from typing import Any from...

What do you think about renaming the directory to simply `uploader` instead of `recording_uploader`?

@KIRA009 what do you think about https://www.cloudflare.com/en-ca/developer-platform/products/r2/: > Forever Free > 10 GB / month