Thank you everyone. I've been contacted by some great people, and for the time being I'm no longer available for freelance. However, if you'd like to establish a contact for possible collaboration at a later date, please feel free to reach out and let's have a talk.
Experience: Among other things, I have developed APIs, contributed to frontend designs, provided database assistance, and helped with production deployment. I do my best to follow industry best practices and deliver clean, maintainable code.
Super, this has inspired me to look more into using a keyboard to write on a Kindle on an external server, and now I have a much better writing set up.
I've found I enjoy writing on Kindle, despite how limited it was. I make notes by highlighting words in a book and writing them down in a note that was associated with the highlighted word. Clunky but it works.
Using an external server is much better though as it works with my keyboard, allows to keep the writing elsewhere. Very happy with it.
> We start by parsing documents into chunks. A sensible default is to chunk documents by token length, typically 1,500 to 3,000 tokens per chunk. However, I found that this didn’t work very well. A better approach might be to chunk by paragraphs (e.g., split on \n\n).
Hmm good insight there. I've done some experimenting formerly by chunk length and it's been pretty troublesome due to missing context.
<center>
<b>notice</b>
<p>javascript required to view this site</p>
<b>why</b>
<p>measured improvement in server performance</p>
<p>awesome incremental search</p>
</center>
It does load faster now that it doesn't display anything.
hallarempt, thanks for making that clear - I have no issue with the project in that case. Also thanks a lot for maintaining Krita, I've used the software in the past and it's been great. I'm especially interested in combining Stable Diffusion with Krita.
That's a surprisingly great idea. A mobile phone can be used as a server, and for their capabilities, they are cheaper than Raspberry Pi when with some issues especially. Out of curiosity I just found an offer for a used Pixel 6 Pro for 70 EUR, supposedly only broken screen and the rest is working, where it has 12GB RAM with CPU Octa-core (copypasting: 2x2.80 GHz Cortex-X1 & 2x2.25 GHz Cortex-A76 & 4x1.80 GHz Cortex-A55), that's a fairly good offer.
I only used the app in the beginning of my language learning with English, so 6 years ago, but the learning was artificial, making you feel good about making no progress, and I was doing the hardest mode they had with 30 experience or something daily. I switched onto real methods of learning such as immersion and Anki later on, which is when I really learned a number of languages. The gamification is fine, but it should be combined with real progress. As an alternative point, Duolingo is fine to start with as in following the paradigm of "starting small", however has to be abandoned shortly after.
Regarding 1) you could watch https://www.youtube.com/watch?v=klTvEwg3oJ4 . Pinecone is a vector database and LLMs can use them to extend their memory beyond their token limit. Where traditionally an LLM can answer only according what's provided in its context, which is limited by a token limit, an LLM can query the database to get information from it such as your name.
Is there any explanation to the negativity expressed here over the name? Because GPT4All was posted 20 days ago here https://news.ycombinator.com/item?id=35349608 with 593 points and 303 comments, and nobody mentioned it.
It's made by the same people here https://github.com/nomic-ai/gpt4all who initially distributed a LLaMA based model finetuned for conversations over torrent. I think you're overly critical. GPT4All naming is fine in my opinion, it's literally "GPT for all", but I can see why people would dislike it.
Depends on whether you trust their base project https://github.com/nomic-ai/gpt4all . gpt4all is actively distributed over torrent, I actually have over 2.0 ratio