jzombie

Curious to know your thoughts on this, then: https://github.com/jzombie/pipper

Coming from a "Poetry background", this makes my life easier to not have to remember the pip/venv commands.

I started a project, not sure if it's a good idea (but it is helpful to me), which helps to make pip/venv a little easier to work with.

It's a set of Bash commands that wrap pip, basically.

https://github.com/jzombie/pipper - Package Installer and Python Project Environment Runner

I originally wasn't a huge fan of Python myself; avoided it for a number of years as much as possible, but have really grown into it lately as I've been doing experimentations in ML.

Have since started using it for other projects basically to just get more familiar with it; and also to take myself rather less seriously and just try to keep things as simple as possible.

It's too bad that there are multiple package managers for Python that all have different approaches, but it is nice that there are at least ways around that, as you've mentioned (just seems like a lot of complexity to do something that seems like it should be easy; installing/upgrading/removing packages).

Thanks for the share! I'll post this in my README as an alternative approach.

"Thin air" is a weird metaphor for something that happens in space, where there is no air.

Having read Napoleon Hill's book, "Think and Grow Rich", several times, and considering the book is now in the public domain, I thought that I would create a custom GPT using the book's epub as the context, and share the book with others.

Any business proposition that begins with "Hey, I hear you're a programmer!" doesn't sound like a good business proposition at all.

I don't know if I totally agree with this. Maybe it's not nearly as bad as how the article frames it but just doing a Google image search of "landfills of old PCs" returns some pretty convincing images.

I think nano LLMs are the next trendy thing, but I agree with your sentiment.

Indeed. A landfill is the worst possible solution for this.

Could potentially.

Sorry to hear that.

Apple Music is the only music subscription I have ever signed up for, and I like it a lot.

Wondering how other music services compare to it.

Thanks for sharing.

I don't personally know.

I've been curious if DALL-E has been truly been mixed in w/ ChatGPT as a single model using a Mixture of Experts (MoE)- type learning gate to train them all together.

Curious as to why some sort of model specifically trained for prompt engineering couldn't be placed before a LLM in a pipeline, or used in a transfer learning scenario.

I'm also curious as to why existing LLMs can't be fine tuned to handle this, if prompt engineering is really a major concern.

Usually, if I don't get the answer I'm looking for from ChatGPT, I tell it it's not the answer I'm looking for, what the original answer was missing, and I usually get a better answer the second time around.

If it goes beyond that I sometimes resort to just cussing at it, and that usually does the trick.

If you could squeeze in LLM integration for that price, somehow undercutting GPT+, but with RAG on your own data, it would be a steal.

> the label wanted more in licensing fees than the whole thing cost to produce.

Hopefully this message was sent instead.

Nice! Thanks for the tip.

Anyway, I appreciate this conversation and am going to make some coffee.

> I think my next attempt will be a handful of hand crafted rules on daily data. I'm definitely never going to try day trading scale strategies or try to pick good points intraday to buy. It should be resilient to the price difference over a day or two

Not sure why HN won't let me reply directly w/o replying this way at times.

I started w/ an LSTM and wound up w/ a mixture of transformers, CNNs and skip connections.

Yes, actually I was planning on training a separate model to determine buy/sell signals, using this prediction model as possibly part of a transfer learning process, and do paper trading w/ it to start w/.

Thanks for the feedback. Will try that. Been mostly using Keras Tuner and Tensorboard to slowly get to the point I'm at and have had some wild results in the process.

I thought MSE was tied to the predictions it makes and not the structure itself (i.e. if you get the same value out for the same input, using different structures, you should at least get the same MSE).

I can assure the data is not shuffled and is ordered in chronological order (time series model).

However at present I've only got training/validation splits and not an additional testing.

No problem.

My apologies for my tone in this thread, as well. Good luck with your learning adventure!

And ChatGPT itself is NOT built using JS or React if that's your question... It's a model built using PyTorch, I believe, using some very expensive hardware.

Just the user interface is [theoretically] coded in React.

Why not just take it for its word?

I don't see, for instance, why they might use Svelte instead, and some evil genius decided to just hardcode that into the window object.

A lot of people actually do this: https://news.ycombinator.com/from?site=discussions.apple.com

I tried that by asking if they could, and they seemed like it wasn't an easy thing to do.

Of course, the first person I talked to didn't know what "Ventura" was, so maybe I called the wrong company.