ashz8888

I did something similar [1], where the text based game being a Text Interface (TI) that provides model a view and a set of actions. The model repeatedly interacts with TI to achieve a goal.

In the current implementation, Text Interface allows the model to list files, open a file, and search within a file to find what it needs to satisfy the goal.

With my current set of prompts, the model is able to backtrack when it fails to find relevant info in the current file. However, I couldn't get it work with GPT-3.5. Only GPT-4 is capable to reason its way through the Text Interface.

[1] https://github.com/ash80/backtracking_gpt

I put some heating pads in socks, gloves, and sometimes jackets, which I found to work better and much more energy efficient.

https://confluo.app - A productivity assistant app that instead of planning your day in advance dynamically suggests you tasks to pick based on the time of the day. Planning ahead never worked for me as something unexpected always came along. Hence I wanted an app that I can open, go through a list of task suggestions and pick the one I like. In addition, I included features like timer, pomodoro, and virtual co-working that helped me stay productive during the lockdowns. I also wanted to track how many hours I was working and which skill I was spending my time on, so I also those features. I shared it on HN, hoping people will like it. But it never made it to new page :(

It depends on your requirements. I have been building www.confluo.app, a social task assistant, in my part-time for about 2 years now. I wanted it:

1) to target both iOS and Android devices

2) to be real-time for social networking and collaborative tasks

3) available in both offline and online modes

4) to have no cost of developing and testing with small audience.

Turned out I could achieve all of the above using Flutter + Firebase (Auth & Firestore).

That’s how I felt when I was working on my own during the lockdowns. The harder I worked the lonelier I became. Sorry for the plug, but to resolve this I built confluo.app to keep others informed as we work. I’m still testing this idea out.

Well because of tradition. Historically it made sense to define new technology node in terms physical gate length. But now even if that's not viable, they continue to do so for better marketing I guess.

Short answer is tradition. Historically they were able to stay on Moore's law with each new technology node representing the physical gate length. Currently however, even if they can't continue on that trajectory they still define the next technology node that way.

Just wanted to point out that 3nm or 2nm are nothing but the marketing terms. The physical channel length will continue to remain at around 10 nm in this decade, irrespective of the device architecture. See Fig. 1.2 of my PhD thesis: https://etheses.whiterose.ac.uk/22492/1/Novel%20Approaches%2...