Hacker News Reader

samlhuillieron Banana Form: Typeform clone that let's you design forms with AI

The output is literally a link, like typeform. And that link will render the design you've customized within the app

samlhuillieron You are what you read, even if you don't always remember it

I like to think of this like fine-tuning LLMs. When you fine-tune an LLM it doesn't pick up and memorise all of the training data. Rather it adjusts its weights/perspectives based on the content trained on/read.

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

Just markdown right now, plain text is coming

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

Not yet!

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

No catch pal

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

Thank you!

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

Interesting. Thanks for sharing will take a look!

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

Thanks for your feedback!

- Multiple vaults is in fact in a PR right now: https://github.com/reorproject/reor/pull/28

- Manual linking is coming.

- Minimizing the UI to chat is interesting. Right now I guess you can drag chat to cover anything - but yes perhaps a toggle between two modes could be interesting.

- Read other formats also something in the pipeline. Just need to sort out the editor itself to support something like this. Perhaps pdfs would just be embedded into the vector db but not accessible to the editor.

- Integrating with browser history and bookmarks is a big feature. Things like web clipping and bringing in context from different places are interesting...

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

Absolutely! Really respect the work you folks are doing.

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

Yes unfortunately not implemented yet. Will be coming soon though :)

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

Thank you for your feedback!

Working hard on improving the chunking to improve related notes section. RAG is fairly naive right now, with lots of improvements coming in the next few weeks.

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

Two reasons:

1. The libraries I used to run models locally didn't work inside a plugin.

2. I believe AI is a fairly big paradigm shift that requires new software.

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

It's filesystem mapping 1:1. Basically the same thing Obsidian does when you open a vault. You can create new files with Reor, create directories and edit existing files. Chunking happens only in vector DB and everything is synced automatically so you shouldn't notice anything if you reopen Reor after using Obsidian.

In short, yes it'd work seamlessly if you wanted to use it occasionally.

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

I agree with this.

In some cases, hard thinking and searching for things manually can really enhance understanding and build your knowledge.

In other cases, particularly when ideating for example, you want to be given "inspiration" from other related ideas to build upon other ideas you've had previously.

I think it's a mix of both - reaching for AI as and when when you need it - but avoiding it intentionally at times as well.

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

If you can convert your One Note notes to markdown files then yes. On startup, you'll be asked to choose your vault directory - which needs to be a directory full of markdown files.

samlhuillieron Show HN: Reor – An AI note-taking app that runs models locally

Absolutely! Would love your help.

samlhuillieron Sorry, but a new prompt for GPT-4 is not a paper

Times are changing. Human researchers will dedicate more and more time towards getting language models to work in desired ways rather than doing the research themselves. Language models will largely be the ones making "research" discoveries. Both should be considered valid research IMO.

samlhuillieron Show HN: AI News Analyst

ChatGPT hasn’t got the faintest idea about today’s news!

samlhuillieron A simple guide to fine tuning Llama 2 on your own data

Legend

samlhuillieron A simple guide to fine-tuning Llama 2

Yes using the qlora adapter that hugging face provides with peft

samlhuillieron A simple guide to fine-tuning Llama 2

Working on this now!

samlhuillieron Ask HN: Is there a recommender system for blog posts or articles?

I mean something curated by algorithms, not humans!

samlhuillieron Ask HN: Is there a recommender system for blog posts or articles?

"Curated by our editors"