promptbench VS Inbox Zero

Fair question.

Evaluate refers to the phase after training to check if the training is good.

Usually the flow goes training -> evaluation -> deployment (what you called inference). This project is aimed for evaluation. Evaluation can be slow (might even be slower than training if you're finetuning on a small domain specific subset)!

So there are [quite](https://github.com/microsoft/promptbench) [a](https://github.com/confident-ai/deepeval) [few](https://github.com/openai/evals) [frameworks](https://github.com/EleutherAI/lm-evaluation-harness) working on evaluation, however, all of them are quite slow, because LLM are slow if you don't have infinite money. [This](https://github.com/open-compass/opencompass) one tries to speed up by parallelizing on multiple computers, but none of them takes advantage of the fact that many evaluation queries might be similar and all try to evaluate on all given queries. And that's where this project might come in handy.

On April 1st 2004, Google released Gmail.

Twenty years later, I'm releasing an open source email app that helps you reach inbox zero for a single day: Simple Email Mode

Simple Mode makes handling less overwhelming:

* Handle emails in batches of 5

* Long emails summarized

* Timer to gamify maintain focus

* Set aside what you want to handle later. Archive the rest

You can try it out at https://getinboxzero.com under the Early Access tab.

And check out the GitHub repo: https://github.com/elie222/inbox-zero

Only for Gmail users at this time.

You can also see when we deploy each time on GitHub: https://github.com/elie222/inbox-zero/deployments